JP6276399B2 - System and method for multi-user multilingual communication - Google Patents

Description

This application claims priority and benefit of US Patent Application Serial No. 13 / 908,979, filed June 3, 2013, incorporated herein by reference in its entirety. To do.

The present invention relates generally to language translation, and more particularly to language translation with multiple users and multiple languages.

BACKGROUND OF THE INVENTION Prior to the advent of machine-based language translation (hereinafter “machine translation”), translation between two languages was possible only by human intervention or interpretation, educated in both languages. In contrast, typical machine translators generally operate based on statistical / probabilistic analysis of context and grammar, usually without the need for human intervention / interpretation.

  Typical machine translations are often prone to errors, especially if the text to be translated has minimal context. Text with minimal context is often found in conversations that employ a concise sentence structure. In addition, machine translation often has problems with abbreviations, acronyms, contractions, colloquial words / phrases, proper nouns, and common nouns. These are also commonly found in conversational text.

SUMMARY OF THE INVENTION Various embodiments described herein provide systems and methods related to multilingual communication between multiple users, possibly in two or more client systems. Modes of communication facilitated by embodiments include Internet-based chat (eg, Apple® iMessage®, Windows® Live Messenger, etc.), email (eg, embedded forum messaging, Yahoo (registered). Trademark) email, RFC 5322, etc.), text-based cellular communications (eg, SMS or MMS messages), posting to online forums (eg, posting to web-based hobby forums), and online social media services (eg, Twitter (registered) Trademark), Facebook, etc.). For example, the system and method may implement a multilingual multiuser chat system.

  For some embodiments, a provided method includes identifying a first language and a second language, and from a first person in a first chat client system communicating in the first language, Receiving an initial message in one language and querying the data store for a first corresponding message in a second language based on the initial message in the first language. If the data store includes a first corresponding message, the method assists in transmitting a message corresponding to a second person in a second chat client system communicating in a second language. Depending on the embodiment, the initial message may include text, emoticons, ASCII base art, or other content suitable or customary for human readable messages sent over the network. In addition, the initial message may be part of a larger message being communicated between chat client systems (eg, the initial message is a sentence in a multi-sentence message).

  If the data store does not include the first corresponding message, the method may attempt to convert at least a portion of the initial message to a converted message in the first language using a conversion engine. Using the transformed message, the method may query the data store for a second corresponding message in a second language based on the transformed message.

  For certain embodiments, the system or method may attempt to convert the initial message using a series of conversion operations before querying the data store for a second corresponding message based on the converted message. Alternatively, in some embodiments, the system or method may perform the conversion and query iteratively so that the initial message is converted using a subset of the available conversion operations, resulting in If the data store is queried for a second corresponding message based on the resulting transformed message and no second corresponding message is identified, another iteration of transformation and query is performed (eg, resulting in The transformed message is further transformed using another subset of available transformation operations and the data store is queried for a second corresponding message based on the resulting transformed message). In some such embodiments, a subset of the transform operations that are applied at each iteration may be applied to the initial message, or may be applied to the resulting latest transformed message.

  Finally, the method may assist in translating the initial message or transformed message into a corresponding message in the second language. In some embodiments, when the first corresponding message for the initial message is not in the data store and the conversion engine does not convert at least a portion of the initial message, the initial message may be translated into a corresponding message. In addition, in various embodiments, when the first corresponding message for the initial message is not in the data store, when the conversion engine yields a converted message that includes conversion of at least a portion of the initial message, and converted When the data store does not contain a second corresponding message for the message, the converted message can be translated into a corresponding message.

  Depending on the embodiment, converting a portion of the initial message identifies a chat term word or phrase (eg, “lol”, “gr8t”) in the initial message, and the chat term word or phrase is not a chat term Replacing with a word or phrase, spell-checking a portion of the initial message, or identifying an abbreviation in a portion of the initial message and replacing the abbreviation with a word or phrase (eg, represented by an abbreviation) (Eg, “CA” with “California” or “brb” with “be right back”).

  Moreover, translating a portion of the initial message identifies an acronym in the portion of the initial message, and the acronym corresponds to an acronym (eg, “USA”), a word or phrase (eg, represented by an acronym). Or identifying a colloquial word or phrase in a portion of the initial message and replacing the colloquial word or phrase with a word or phrase representing the colloquial word or phrase. Further, translating a portion of the initial message identifies obscene words or phrases in the initial message portion, and obscene words or phrases (eg, represent obscene words or phrases) Substituting with unintended words or phrases, or removing obscene words or phrases from the initial message.

  For some embodiments, translating a portion of the initial message includes flagging the portion of the initial message so that it is not translated. For example, certain parts of the initial message include proper nouns, common nouns, contractions, abbreviations, or acronyms, and the method may flag the certain parts so that they are not translated in subsequent actions.

  Certain embodiments provide a system that includes various components configured to perform the various operations described herein. Similarly, certain embodiments provide a computer program product that includes computer instruction code configured to cause a computer system to perform various operations described herein.

  In one aspect, the invention relates to a computer-implemented method. The method includes selecting a word or phrase from a data store that is associated with a translation failure from a first language to a second language of a message that includes the word or phrase, and prompting a user for user feedback on the translation failure. Selecting a value of an incentive to provide to the user in exchange for the user feedback, and transmitting a request for the feedback to the user computing device, the request including the incentive And the method further comprises receiving the user feedback from the computing device, the user feedback including the respective word or phrase of the first or second language, and the method. In addition, the above user feedback Includes determining to be approved, based on the approval, according to the value of the incentive and providing credit to the account of the user.

  In one embodiment, the failure is due to an actual failure in translation of the message. The failure can be identified by flagging the message as potentially inaccurate or by flagging the message. Selecting the user may be based on the user's certainty measure, the quota associated with the user, the user's previous credit for the account, the user's preferences, or the user's language skills. In some embodiments, the word or phrase includes a chat term in the first language. The response may include the chat language in the second language. In some implementations, the query includes a field configured to receive a text-based value.

  In certain embodiments, the request includes a pre-selected set of definitions from which the user can select a definition for the word or phrase. The set of pre-selected definitions may include, for example, at least one definition provided by another user in response to another request, the other request previously for the word or phrase from the other user. Previously generated to get user feedback. The other request may include another set of the preselected definitions from which the other user has selected the definition. The method may further include evaluating the user feedback to determine the most common response.

  In various embodiments, the method further includes determining the suitability of the user based on the user feedback. The method may further include updating the translation or translation of the word or phrase from the first language to the second language based on the user feedback. In some embodiments, determining that the user feedback is approved may include determining that the user feedback is not fraudulent and / or determining that the user feedback is accurate. . Determining that the user feedback is approved may be based on a comparison of the user feedback to at least one previous user feedback provided by another user in response to the other request, where the other request is: Previously generated to get feedback on the word or phrase from the other user.

  In certain embodiments, the incentive includes (or is an offer for) in-game currency or in-game items. The value of the incentive may be determined based on, for example, the complexity of the word or phrase or the importance of the word or phrase. In some examples, determining the value of the incentive includes: (i) complexity of the word or phrase; (ii) importance of the word or phrase; (iii) response method used by the user; (Iv) consider the type of word or phrase, and / or (v) the language involved in the translation failure.

  In another aspect, the invention relates to a system that includes one or more computers programmed to perform operations. The operation selects a word or phrase from a data store that is associated with a translation failure from a first language to a second language of a message that includes the word or phrase and prompts a user for user feedback on the translation failure. Selecting a value of an incentive to provide to the user in exchange for the user feedback, and transmitting a request for the feedback to the user computing device, the request including the incentive And the operation further includes receiving the user feedback from the computing device, the user feedback including each word or phrase in the first or second language, and the operation In addition, the above user feedback Includes determining to be approved, and providing credit to the account of the user based on the approval.

  In one embodiment, the failure is due to an actual failure in translation of the message. The failure can be identified by the user flagging the message as potentially inaccurate or by flagging. Selecting the user may be based on the user's certainty measure, the quota associated with the user, the user's previous credit for the account, the user's preferences, or the user's language skills. In some embodiments, the word or phrase includes a chat term in the first language. The response may include a second language chat term. In some implementations, the query includes a field configured to receive a text-based value.

  In certain embodiments, the request includes a pre-selected set of definitions from which the user can select a definition for the word or phrase. The set of pre-selected definitions may include, for example, at least one definition provided by another user in response to another request, the other request previously for the word or phrase from the other user. Previously generated to get user feedback. The other request may include another set of the preselected definitions from which the other user has selected the definition. The operations may further include evaluating the user feedback to determine the most common response.

  In various embodiments, the operation further includes determining the suitability of the user based on the user feedback. The operation may further include updating the translation or translation of the word or phrase from the first language to the second language based on the user feedback. In some embodiments, determining that the user feedback is approved may include determining that the user feedback is not fraudulent and / or determining that the user feedback is accurate. . Determining that the user feedback is approved may be based on a comparison of the user feedback to at least one previous user feedback provided by another user in response to the other request, where the other request is: Previously generated to get feedback on the word or phrase from the other user.

  In certain embodiments, the incentive includes (or is an offer for) in-game currency or in-game items. The value of the incentive may be determined based on, for example, the complexity of the word or phrase or the importance of the word or phrase. In some examples, determining the value of the incentive includes: (i) complexity of the word or phrase; (ii) importance of the word or phrase; (iii) response method used by the user; (Iv) consider the type of word or phrase, and / or (v) the language involved in the translation failure.

  In another aspect, the invention relates to a computer program product stored on one or more storage media for improving language translation through feedback provided with incentives. The computer program product includes: the data processing device selecting from a data store a word or phrase associated with a translation failure from a first language to a second language of a message containing the word or phrase; and the translation Selecting a user for user feedback on failure, determining a value of an incentive to provide to the user in exchange for the user feedback, and sending a request for the feedback to the user computing device. And the request includes the incentive, and the computer program product is further transmitted from the computing device to the user feedback. The user feedback is executable by the data processing device to perform an action including receiving, the user feedback includes a respective word or phrase of the first or second language, and the computer program product further includes: The data processing device can be executed by the data processing device to perform an operation including determining that the user feedback is approved and granting a credit to the user's account based on the approval.

  In one embodiment, the failure is due to an actual failure in translation of the message. The failure can be identified by the user flagging the message as potentially inaccurate or by flagging. Selecting the user may be based on the user's certainty measure, the quota associated with the user, the user's previous credit for the account, the user's preferences, or the user's language skills. In some embodiments, the word or phrase includes a chat term in the first language. The response may include a second language chat term. In some implementations, the query includes a field configured to receive a text-based value.

  In certain embodiments, the request includes a pre-selected set of definitions from which the user can select a definition for the word or phrase. The set of pre-selected definitions may include, for example, at least one definition provided by another user in response to another request, the other request previously for the word or phrase from the other user. Previously generated to get user feedback. The other request may include another set of the preselected definitions from which the other user has selected the definition. The operations may further include evaluating the user feedback to determine the most common response.

  In various embodiments, the operation further includes determining the suitability of the user based on the user feedback. The operation may further include updating the translation or translation of the word or phrase from the first language to the second language based on the user feedback. In some embodiments, determining that the user feedback is approved may include determining that the user feedback is not fraudulent and / or determining that the user feedback is accurate. . Determining that the user feedback is approved may be based on a comparison of the user feedback to at least one previous user feedback provided by another user in response to the other request, where the other request is: Previously generated to get feedback on the word or phrase from the other user.

  In certain embodiments, the incentive includes (or is an offer for) in-game currency or in-game items. The value of the incentive may be determined based on, for example, the complexity of the word or phrase or the importance of the word or phrase. In some examples, determining the value of the incentive includes: (i) complexity of the word or phrase; (ii) importance of the word or phrase; (iii) response method used by the user; (Iv) consider the type of word or phrase, and / or (v) the language involved in the translation failure.

  In one aspect, the present invention relates to a method implemented by a data processing apparatus. The method includes providing a text message chat system to a plurality of users, receiving an original text message in a first language from a first user, and an initial translation of the original text message in a second language. Generating, providing the second user with the original text message and the first translation, receiving translation corrections from the second user to account for errors in the first translation; (a ) Identifying the most accurate translation correction from a plurality of translation corrections including the translation correction from the second user, and (b) of word-based features, language-based features, and word alignment features Evaluating the accuracy of the translation correction from the second user using at least one of Chi comprising at least one.

  In certain embodiments, the method includes providing an incentive (eg, virtual goods and / or virtual currency used in online games) to encourage the second user to submit the translation correction. . Determining the most accurate translation correction may include receiving at least one additional translation correction from at least one additional user to accommodate an error in the initial translation, the at least one One additional translation correction and the translation correction from the second user define the plurality of translation corrections, and determining the most accurate translation correction further includes determining the plurality of translation corrections. Receiving feedback from the user regarding accuracy and identifying the most accurate translation correction from the plurality of translation corrections based on the feedback.

  In some implementations, the method further includes providing a reward (eg, virtual goods and / or virtual currency used in online games) to the user who submitted the most accurate translation correction. The method may further include providing a reward (eg, virtual goods and / or virtual currency used in online games) to a user who provided feedback used to identify the most accurate translation. Word-based features may include, for example, word counts, letter counts, pictograms, numbers and / or punctuation marks. Using the language-based feature may include identifying parts of speech in the original text message and the translation correction from the second user.

  In some embodiments, the method further includes identifying the number of verbs present in each of the original text message and the translation correction from the second user, and the number of verbs in the original text message. Comparing the number of verbs in the translation correction from the second user. A lack of part of speech in the original text message and / or the translation correction from the second user may indicate a language detection failure. The method may further include rejecting the translation modification from the second user if the translation modification from the second user is the same as the first translation.

  In another aspect, the present invention relates to a system including a computer readable medium having instructions stored thereon and a data processing device. The data processing apparatus provides a text message chat system to a plurality of users, receives an original text message in a first language from a first user, and an initial of a second language in the original text message. Generating a translation; providing the original user with the original text message and the first translation; receiving translation corrections from the second user to account for errors in the first translation; (A) identifying the most accurate translation correction from a plurality of translation corrections including the translation correction from the second user, and (b) word-based features, language-based features, and / or words Using alignment features to evaluate the accuracy of the translation correction from the second user; Chino configured to execute instructions to perform the operations including the performing at least one.

  In certain embodiments, the action includes providing an incentive (eg, virtual goods and / or virtual currency used in online games) to encourage the second user to submit the translation correction. . Determining the most accurate translation correction may include receiving at least one additional translation correction from at least one additional user to accommodate an error in the initial translation, the at least one One additional translation correction and the translation correction from the second user define the plurality of translation corrections, and determining the most accurate translation correction further includes determining the plurality of translation corrections. Receiving feedback from the user regarding accuracy and identifying the most accurate translation correction from the plurality of translation corrections based on the feedback.

  In some implementations, the operation further includes providing a reward (eg, virtual goods and / or virtual currency used in online games) to the user who submitted the most accurate translation correction. The operations may further include providing rewards (eg, virtual goods and / or virtual currency used in online games) to users who have provided feedback used to identify the most accurate translations. Word-based features may include, for example, word counts, letter counts, pictograms, numbers and / or punctuation marks. Using the language-based feature may include identifying parts of speech in the original text message and the translation correction from the second user.

  In some embodiments, the action further identifies the number of verbs present in each of the original text message and the translation correction from the second user, and the number of verbs in the original text message. Comparing with the number of verbs in the translation correction from the second user. A lack of part of speech in the original text message and / or the translation correction from the second user may indicate a language detection failure. The operation may further include rejecting the translation correction from the second user if the translation correction from the second user is the same as the initial translation.

  In another aspect, the present invention relates to a computer program product stored on one or more storage media for controlling the processing mode of a data processing device. In the computer program product, the data processing device provides a text message chat system to a plurality of users, receives an original text message in a first language from a first user, Generating an initial translation of two languages, providing the original user with the original text message and the first translation, and translating from the second user to respond to an error in the first translation Receiving a correction; (a) identifying the most accurate translation correction from a plurality of translation corrections including the translation correction from the second user; and (b) a word-based feature, a language-based feature. And / or using at least one of the characteristics of word alignment Serial executable by said data processing apparatus to perform operations including at least one of evaluating the accuracy of the translation modifications from the second user.

  In certain embodiments, the action includes providing an incentive (eg, virtual goods and / or virtual currency used in online games) to encourage the second user to submit the translation correction. . Determining the most accurate translation correction may include receiving at least one additional translation correction from at least one additional user to accommodate an error in the initial translation, the at least one One additional translation correction and the translation correction from the second user define the plurality of translation corrections, and determining the most accurate translation correction further includes determining the plurality of translation corrections. Receiving feedback from the user regarding accuracy and identifying the most accurate translation correction from the plurality of translation corrections based on the feedback.

  In some implementations, the operation further includes providing a reward (eg, virtual goods and / or virtual currency used in online games) to the user who submitted the most accurate translation correction. The operations may further include providing rewards (eg, virtual goods and / or virtual currency used in online games) to users who have provided feedback used to identify the most accurate translations. Word-based features may include, for example, word counts, letter counts, pictograms, numbers and / or punctuation marks. Using the language-based feature may include identifying parts of speech in the original text message and the translation correction from the second user.

  In some embodiments, the action identifies the number of verbs present in each of the original text message and the translation correction from the second user, and determines the number of verbs in the original text message. And comparing with the number of verbs in the translation correction from a second user. A lack of part of speech in the original text message and / or the translation correction from the second user may indicate a language detection failure. The operation may include rejecting the translation correction from the second user if the translation correction from the second user is the same as the initial translation.

  In one aspect, the present invention relates to a method implemented by a data processing apparatus. The method includes identifying a first language and a second language, and audible chat terms in the first language from a first person in a first chat client system communicating in the first language. Receiving a message, converting the chat term audible message into a chat language text message in the first language, and converting the chat term text message into a plain language text message in the first language. Translating the plain language text message into a corresponding plain language text message in the second language; and converting the corresponding plain language text message into the corresponding chat term in the second language. Convert to text message and corresponding chat term text message above Switching to a corresponding chat term audible message in the second language; and sending the corresponding chat term audible message to a second person in a second chat client system communicating in the second language. Including.

  In an embodiment, converting the chat term audible message to the first language chat term text message includes providing the chat term audible message to a speech recognition system. The conversion of the chat term text message may include identifying a chat term word or phrase in the chat term text message and replacing the chat term word or phrase with a non-chat word or phrase. . In some examples, converting the corresponding chat term text message to a corresponding chat term audible message in the second language provides the corresponding chat term text message to a text-to-speech system. including.

  In one implementation, the speech recognition system and / or the text-to-speech system uses data that includes multiple accents and dialects for each of the first and second languages. The data may include a chat term and plain language format for each of the first and second languages. In various embodiments, the method receives feedback from a user regarding the accuracy of at least one of the corresponding plain language text message, the corresponding chat term text message, and / or the corresponding chat term audible message. Including that. The method may further include offering an incentive to the user (eg, virtual goods and / or virtual currency used in online games) for providing feedback. In some cases, the method includes processing feedback to improve the accuracy of the speech recognition system and / or the text-to-speech system.

  In another aspect, the invention relates to a system including a computer readable medium storing instructions and a data processing device. The data processing device identifies a first language and a second language, and receives a chat in the first language from a first person in a first chat client system communicating in the first language. Receiving a term audible message, converting the chat term audible message into a chat language text message in the first language, and converting the chat term text message into a plain language text message in the first language. Translating the plain language text message into a corresponding plain language text message in the second language and corresponding the plain language text message in the second language. Convert to chat term text message and corresponding chat term text above Converting a message to a corresponding chat term audible message in the second language, and sending the corresponding chat term audible message to a second person in a second chat client system communicating in the second language. Are configured to execute instructions to perform operations including:

  In an embodiment, converting the chat term audible message to the first language chat term text message includes providing the chat term audible message to a speech recognition system. Converting the chat term text message includes identifying a chat term word or phrase in the chat term text message and replacing the chat term word or phrase with a non-chat word or phrase. May be included. In some examples, converting the corresponding chat term text message to a corresponding chat term audible message in the second language provides the corresponding chat term text message to a text-to-speech system. including.

  In one implementation, the speech recognition system and / or the text-to-speech system uses data that includes multiple accents and dialects for each of the first and second languages. The data may include a chat term and plain language format for each of the first and second languages. In various embodiments, the response includes receiving feedback from a user regarding the accuracy of the corresponding plain language text message, the corresponding chat term text message, and / or the corresponding chat term audible message. . The operations may further include providing incentives to the user (eg, virtual goods and / or virtual currency used in online games) for providing feedback. In some cases, the operations include processing feedback to improve the accuracy of the speech recognition system and / or text-to-speech system.

  In another aspect, the present invention relates to a computer program product stored on one or more storage media for controlling a processing mode of a data processing device. The computer program product is obtained from the first person in the first chat client system in which the data processing apparatus identifies the first language and the second language and communicates in the first language. Receiving a chat term audible message in a first language; converting the chat term audible message to a chat term text message in the first language; and converting the chat term text message into a plain language in the first language. Converting into a plain text message, translating the plain text message into a corresponding plain text message in the second language, and converting the corresponding plain text message into the first text message. Convert to the corresponding chat term text message in two languages Converting the corresponding chat term text message into a corresponding chat term audible message in the second language, and sending a second person in a second chat client system communicating in the second language to the second person The data processing device can perform the operations including sending a corresponding chat term audible message.

  In an embodiment, converting the chat term audible message to the first language chat term text message includes providing the chat term audible message to a speech recognition system. Converting the chat term text message includes identifying a chat term word or phrase in the chat term text message and replacing the chat term word or phrase with a non-chat word or phrase. May be included. In some examples, converting the corresponding chat term text message to a corresponding chat term audible message in the second language provides the corresponding chat term text message to a text-to-speech system. including.

  In one implementation, the speech recognition system and / or the text-to-speech system uses data that includes multiple accents and dialects for each of the first and second languages. The data may include a chat term and plain language format for each of the first and second languages. In various embodiments, the action comprises receiving feedback from a user regarding the accuracy of the corresponding plain text message, the corresponding chat term text message, and / or the corresponding chat term audible message. Including. The operations may further include providing incentives to the user (eg, virtual goods and / or virtual currency used in online games) for providing feedback. In some cases, the operations include processing feedback to improve the accuracy of the speech recognition system and / or text-to-speech system.

  In one aspect, the present invention relates to a method implemented by a data processing apparatus. The method includes old training data (e.g. including one or more old text messages with known correct translations into different languages) and one or more newer (e.g. with known correct translations into the different languages). Selecting a mix of new training data (including text messages) and (i) a respective request for a user to translate at least one of the old training data and the new training data, and / or (ii) ) Sending a plurality of respective requests including respective incentives for the translation to a user client device (or a plurality of client devices of a plurality of users) at different times, and after sending a specific request, the specific request About the above old training data Receiving a translation from, comparing the received translation with the correct translation for the old training data, determining the accuracy of the received translation based on the comparison, and the translation Updating the certainty score for the user based on. The certainty score then represents the likelihood that the user will provide an accurate translation of the text message into the different language.

  In some embodiments, the user is an online game participant. Each of these incentives may include virtual goods and / or virtual currency for online games, for example. Determining the accuracy of the translation received from the user may include (i) calculating a word error rate (WER) and / or (ii) bilingual evaluation understudy (BLEU). Using. In some cases, updating the certainty score for the user includes using item response theory to identify deviations from standards in the accuracy of the user's translation. The method may further include revoking the user's translation authority when the certainty score falls below a threshold.

  In various implementations, the method includes providing the user with the respective incentive if the user's translation is determined to be correct. The method may further include detecting a collusion between the user and the second user by identifying a preexisting relationship between the user and the second user. In one example, identifying the preexisting relationship includes analyzing a social network of at least one of the user and the second user.

  In another aspect, the present invention relates to a system including a computer readable medium having instructions stored thereon and a data processing device. The data processing device includes old training data (eg, including one or more old text messages whose correct translations into different languages are known) and one or more whose correct translations into the different languages are not known (eg, Selecting a mix of new training data (including new text messages) and (i) a respective request for a user to translate at least one of the old training data and the new training data, and / or (Ii) sending a plurality of respective requests including respective incentives for the translation to a user's client device (or a plurality of user devices of a plurality of users) at different times, and sending the specific request and then specifying the specific The above-mentioned old training data Receiving a translation from an ant device, comparing the received translation with the correct translation for the old training data, and determining the accuracy of the received translation based on the comparison; An instruction is configured to perform an action including updating a certainty score for the user based on the translation. The certainty score then represents the likelihood that the user will provide an accurate translation of the text message into the different language.

  In one embodiment, the user is an online game participant. Each of these incentives may include virtual goods and / or virtual currency for online games, for example. Determining the accuracy of the translation received from the user may include (i) calculating a word error rate (WER) and / or (ii) bilingual evaluation understudy (BLEU). Using. In some cases, updating the certainty score for the user includes using item response theory to identify deviations from standards in the accuracy of the user's translation. The operation may further include revoking the user's translation authority when the certainty score falls below a threshold.

  In various implementations, the operations include providing the respective incentives to the user if the user's translation is determined to be correct. The operation may further include detecting a collusion between the user and the second user by identifying a preexisting relationship between the user and the second user. In one example, identifying the preexisting relationship includes analyzing a social network of at least one of the user and the second user.

  In another aspect, the present invention relates to a computer program product stored on one or more storage media for controlling a processing mode of a data processing device. The computer program product includes the old training data (eg, including one or more old text messages whose correct translation into different languages is known) and the correct translation (eg, correct translation into the different languages). Selecting a mixture of new training data (including one or more new text messages for which is not known) and (i) a user translating at least one of the old training data and the new training data, respectively Request and / or (ii) sending a plurality of respective requests including respective incentives to the translation to a user's client device (or a plurality of users' multiple client devices) at different times; After sending, on the above specific request Receiving a translation from the client device for the old training data, comparing the received translation with the correct translation for the old training data, and based on the comparison, verifying the accuracy of the received translation. It can be performed by the data processing device to perform an operation including determining and updating a certainty score for the user based on the translation. The certainty score then represents the likelihood that the user will provide an accurate translation of the text message into the different language.

  In some embodiments, the user is an online game participant. Each of these incentives may include virtual goods and / or virtual currency for online games, for example. Determining the accuracy of the translation received from the user may include (i) calculating a word error rate (WER) and / or (ii) bilingual evaluation understudy (BLEU). Using. In some cases, updating the certainty score for the user includes using item response theory to identify deviations from standards in the accuracy of the user's translation. The operation may further include revoking the user's translation authority when the certainty score falls below a threshold.

  In various implementations, the operations include providing each user with an incentive if the user's translation is determined to be correct. The operation may further include detecting a collusion between the user and the second user by identifying a preexisting relationship between the user and the second user. In one example, identifying the preexisting relationship includes analyzing a social network of at least one of the user and the second user.

  In one aspect, the present invention relates to a method implemented by a data processing apparatus. The method includes obtaining a text message in a first language that includes at least one word, providing the text message to a machine translation system, and obtaining a translation of the text message from the machine translation system. Determining that the text message and the translation both include the at least one word of the first language and that the at least one word is spelled correctly; (a ) Determining the frequency with which the at least one word appears in previous text messages; (b) determining the Bayesian probabilities for adjacent words that appear before and after the at least one word; and (c) synonyms. K-means clustering is implemented to identify clusters of words that contain And a to perform one or more of that. If the frequency is above a first threshold, if the Bayesian probability is above a second threshold, and / or if the cluster contains the at least one word, then the method is in a data store Adding the at least one word to the vocabulary.

  In one embodiment, the at least one word includes a word that is not in the vocabulary or is a word that is not in the vocabulary. The at least one word may be a new chat term word or may include the new chat term word. The method may include determining whether the vocabulary in the data store includes the at least one word. The text message may be received from a player client device in an online game. In various examples, the vocabulary includes or consists of words in the first language vocabulary.

  Determining the Bayesian probability occurs (i) considers previous use of the at least one word in the previous text message, and (ii) appears before and after the at least one word in the previous text message. If there is a word, it may include identifying the word. The Bayesian probability may provide an indication of the likelihood that the adjacent word will appear before and after the at least one word in the text message.

  In various implementations, identifying the cluster includes reviewing previous text messages and identifying words that are used as the at least one word in the text message in a similar context. . The method may further include analyzing the syntax and meaning of the text message to determine parts of speech that are present in the text message.

  In another aspect, the present invention relates to a system including a computer readable medium having instructions stored thereon and a data processing device. The data processing device obtains a text message in a first language including at least one word, provides the text message to a machine translation system, and obtains a translation of the text message from the machine translation system And determining that the text message and the translation both include the at least one word in the first language, and that the at least one word is spelled correctly; (A) determining the frequency with which the at least one word appears in previous text messages; (b) determining the Bayesian probabilities for adjacent words that appear before and after the at least one word; and (c) K-means cluster to identify clusters of words containing synonyms Configured to execute the instructions to perform operations including and performing one or more of performing a ring. If the frequency is above a first threshold, if the Bayesian probability is above a second threshold, and / or if the cluster contains the at least one word, then the method is in a data store Adding the at least one word to the vocabulary.

  In one embodiment, the at least one word includes a word that is not in the vocabulary or is a word that is not in the vocabulary. The at least one word may be a new chat term word or may include the new chat term word. The operation may include determining whether the vocabulary in the data store includes the at least one word. The text message may be received from a player client device in an online game. In various examples, the vocabulary includes or consists of words in the first language vocabulary.

  Determining the Bayesian probability occurs (i) considers previous use of the at least one word in the previous text message, and (ii) appears before and after the at least one word in the previous text message. If there is a word, it may include identifying the word. The Bayesian probability may provide an indication of the likelihood that the adjacent word will appear before and after the at least one word in the text message.

  In various implementations, identifying the cluster includes reviewing previous text messages and identifying words that are used as the at least one word in the text message in a similar context. . The operations may further include analyzing the syntax and meaning of the text message to determine parts of speech that are present in the text message.

  In another aspect, the present invention relates to a computer program product stored on one or more storage media for controlling a processing mode of a data processing device. In the computer program product, the data processing device obtains a text message in a first language including at least one word, provides the text message to a machine translation system, and transmits the text message from the machine translation system. Obtaining a translation of the text message; both the text message and the translation include the at least one word of the first language; and the at least one word is spelled correctly. (A) determining the frequency at which the at least one word appears in previous text messages; (b) determining the Bayesian probability for adjacent words that appear before and after the at least one word. And (c) words including synonyms Executable by said data processing apparatus to perform operations comprising and performing one or more of the performing the identifying so k-means clustering clusters. If the frequency is above a first threshold, if the Bayesian probability is above a second threshold, and / or if the cluster contains the at least one word, then the method is in a data store Adding the at least one word to the vocabulary.

  In one embodiment, the at least one word includes a word that is not in the vocabulary or is a word that is not in the vocabulary. The at least one word may be a new chat term word or may include the new chat term word. The operation may include determining whether the vocabulary in the data store includes the at least one word. The text message may be received from a player client device in an online game. In various examples, the vocabulary includes or consists of words in the first language vocabulary.

  Determining the Bayesian probability occurs (i) considers previous use of the at least one word in the previous text message, and (ii) appears before and after the at least one word in the previous text message. If there is a word, it may include identifying the word. The Bayesian probability may provide an indication of the likelihood that the adjacent word will appear before and after the at least one word in the text message.

  In various implementations, identifying the cluster includes reviewing previous text messages and identifying words that are used as the at least one word in the text message in a similar context. . The operations may further include analyzing the syntax and meaning of the text message to determine parts of speech that are present in the text message.

  In one aspect, the present invention relates to a method implemented by a data processing apparatus. The method includes (a) receiving a request from a multi-user chat session to review a history portion of a text message, the history including a plurality of text messages, each text message being in a respective language. And the method further includes (b) (i) selecting a different text message from the portion of the text message history, and (ii) selecting Performing a plurality of parallel processes each including translating the translated text message into a target language; and (c) providing the translated text message to the user's client device from the plurality of parallel processes. , (D) Different parts of the text message history The includes receiving a request to consider, and repeating the step (e) (b) and for the different parts of the history of the text message (c).

  In some embodiments, selecting the different respective text messages includes querying a storage device for the portion of the text message history. Translating the selected text message may include converting at least a portion of the text message from chat terms to plain language. In some implementations, the method includes receiving a request from the user to stop viewing the history of the text message. The plurality of parallel processes may include one process for each respective chat session participant. Alternatively or additionally, the plurality of parallel processes may include one process for each language used in the respective chat session.

  In another aspect, the present invention relates to a system including a computer readable medium having instructions stored thereon and a data processing device. The data processing device is configured to execute an instruction to perform an action including receiving a request from a multi-user chat session to review a history portion of a text message, wherein the history includes a plurality of history Each text message is in a respective language and is sent from each chat session participant, the data processing device further comprising: (b) (i) a history of the text message Selecting multiple different text messages from the portion; (ii) performing a plurality of parallel processes each including translating the selected text message into a target language; and (c) translated Send text messages from multiple parallel processes to the user's client Providing to the device; (d) receiving a request to consider different parts of the history of the text message; and (e) steps (b) and (c) for the different parts of the history of the text message. Instructions are configured to perform operations including repeating.

  In some embodiments, selecting the different respective text messages includes querying a storage device for the portion of the text message history. Translating the selected text message may include converting at least a portion of the text message from chat terms to plain language. In some implementations, the operation includes receiving a request from the user to stop browsing the text message history. The plurality of parallel processes may include one process for each respective chat session participant. Alternatively or additionally, the plurality of parallel processes may include one process for each language used in the respective chat session.

  In another aspect, the present invention relates to a computer program product stored on one or more storage media for controlling a processing mode of a data processing device. The computer program product is executable by the data processing device to perform an operation that includes receiving a request from a multi-user chat session for the data processing device to review a history portion of a text message, The history includes a plurality of text messages, each text message is in a respective language, and is transmitted from each chat session participant, and the computer program product further includes: b) a plurality of parallel processes each comprising: (i) selecting each different text message from the portion of the text message history; and (ii) translating the selected text message into a target language. Do (C) providing the translated text message to the user's client device from the plurality of parallel processes; (d) receiving a request to review different parts of the history of the text message; ) The data processing apparatus can perform the operation including repeating steps (b) and (c) for the different parts of the text message history.

  In some embodiments, selecting the different respective text messages includes querying a storage device for the portion of the text message history. Translating the selected text message may include converting at least a portion of the text message from chat terms to plain language. In some implementations, the operation includes receiving a request from the user to stop browsing the text message history. The plurality of parallel processes may include one process for each respective chat session participant. Alternatively or additionally, the plurality of parallel processes may include one process for each language used in the respective chat session.

  In one aspect, the present invention relates to a method implemented by a data processing apparatus. The method includes providing a text message chat system to a plurality of users (eg, in an online game) and requesting from the first user of the text message chat system to block a second user of the text message chat system. And preventing a text message from the second user from being displayed to the first user after receiving the request.

  In one embodiment, the method blocks a future invitation from the second user to the first user to join a chat session using the text message chat system after receiving the request. In addition. The method may include receiving a second request from the first user to unblock the second user. In some cases, the method includes allowing a text message from the second user to be displayed to the first user after receipt of the second request. The method allows a future invitation to be sent from the second user to the first user to join a chat session using the text message chat system after receiving the second request. Can include.

  In some embodiments, the plurality of users include or define an alliance in the online game. The method may include translating at least a portion of a text message in the text message chat system from a first language to a second language. The method may further include converting at least a portion of the text message from chat terms to plain language. In some implementations, translating and / or transforming may include or utilize parallel processes. For example, the parallel process may include or utilize one process for each of the plurality of users of the chat system (or one process for each language used by the user).

  In another aspect, the present invention relates to a system including a computer readable medium having instructions stored thereon and a data processing device. The data processing device provides a text message chat system to a plurality of users (eg, in an online game) and a first user of the text message chat system to block a second user of the text message chat system Executing an instruction to perform an operation including receiving a request from the server and preventing a text message from the second user from being displayed to the first user after receiving the request. Configured to do.

  In one embodiment, the operation blocks a future invitation from the second user to the first user to join a chat session using the text message chat system after receiving the request. In addition. The operation may include receiving a second request from the first user to unblock the second user. In some cases, the operation includes allowing a text message from the second user to be displayed to the first user after receipt of the second request. The operation permits a future invitation from the second user to be sent to the first user to join a chat session using the text message chat system after receiving the second request. May further include.

  In some embodiments, the plurality of users include or define an alliance in the online game. The operation may include translating at least a portion of a text message in the text message chat system from a first language to a second language. The operation may further include converting at least a portion of the text message from chat terms to plain language. In some implementations, translating and / or transforming may include or utilize parallel processes. For example, the parallel process may include or utilize one process for each of the plurality of users of the chat system (or one process for each language used by the user).

  In another aspect, the present invention relates to a computer program product stored on one or more storage media for controlling a processing mode of a data processing device. The computer program product includes a text message chat system in which the data processing device provides a text message chat system to a plurality of users (eg, in an online game) and blocks a second user of the text message chat system. Receiving a request from a first user of the system and preventing a text message from the second user from being displayed to the first user after receiving the request. Can be performed by the data processing device.

  In one embodiment, the operation blocks a future invitation from the second user to the first user to join a chat session using the text message chat system after receiving the request. Including that. The operation may include receiving a second request from the first user to unblock the second user. In some cases, after receiving the second request, the action includes allowing a text message from the second user to be displayed to the first user. After receiving the second request, the operation allows a future invitation to be sent from the second user to the first user to join a chat session using the text message chat system. Can include.

  In some embodiments, the plurality of users include or define an alliance in the online game. The operation may include translating at least a portion of a text message in the text message chat system from a first language to a second language. The operation may further include converting at least a portion of the text message from chat terms to plain language. In some implementations, translating and / or transforming may include or utilize parallel processes. For example, the parallel process may include or utilize one process for each of the plurality of users of the chat system (or one process for each language used by the user).

  Elements of the embodiments described with respect to a given aspect of the invention may be used in various embodiments of other aspects of the invention. For example, it can be considered. The features of the dependent claims dependent on one independent claim may be used in the apparatus and / or method of any of the other independent claims.

  Other features and aspects of the various embodiments will become apparent from the following detailed description when read in conjunction with the accompanying drawings. The accompanying drawings illustrate, by way of example, the features of such embodiments.

  Various embodiments are described in detail with reference to the following figures. The drawings are provided for illustrative purposes only and depict some embodiments only. These drawings should not be construed as limiting the width, scope or applicability of the embodiments.

1 is a block diagram illustrating an exemplary environment utilizing a multilingual communication system according to various embodiments. FIG. 1 is a block diagram illustrating an exemplary communication conversion and translation system according to various embodiments. FIG. FIG. 6 is a block diagram illustrating an exemplary conversion module according to various embodiments. 1 is a block diagram illustrating an exemplary chat client system according to various embodiments. FIG. 6 is a flowchart illustrating an exemplary method of multilingual communication according to various embodiments. 6 is a flowchart illustrating an exemplary method for converting communications according to various embodiments. FIG. 3 illustrates an exemplary multilingual chat session between chat client systems according to various embodiments. 6 is a flowchart illustrating operations of an exemplary multilingual communication method according to various embodiments. 6 is a flowchart illustrating operations of an exemplary multilingual communication method according to various embodiments. 6 is a flowchart illustrating operations of an exemplary multilingual communication method according to various embodiments. 6 is a flowchart illustrating operations of an exemplary multilingual communication method according to various embodiments. FIG. 6 is a block diagram illustrating an exemplary digital device that may be utilized in accordance with the implementation of various embodiments. FIG. 2 is a block diagram illustrating an exemplary user feedback system in accordance with various embodiments. FIG. 2 is a block diagram illustrating an exemplary user feedback client system in accordance with various embodiments. 6 is a flowchart illustrating an exemplary method for user feedback in accordance with various embodiments. FIG. 6 is a block diagram illustrating an exemplary data flow for a user feedback system in accordance with various embodiments. FIG. 6 is a screenshot illustrating an example of receiving user feedback for a word in accordance with various embodiments. FIG. 7 is a screenshot illustrating an example of skipping user feedback in accordance with various embodiments. FIG. 6 is a screenshot illustrating an example of receiving user feedback for a phrase in accordance with various embodiments. FIG. 6 is a screenshot illustrating an example of receiving user feedback through a list of select form responses according to various embodiments. FIG. 6 is a screenshot illustrating an example of creating a list of select form responses according to various embodiments. FIG. 6 is a screenshot illustrating an exemplary incentive notification in accordance with various embodiments. FIG. 6 is a screenshot illustrating an example when translation fails between client chat systems, in accordance with various embodiments. FIG. 6 is a screenshot illustrating an exemplary list of words or phrases available for user feedback in accordance with various embodiments. FIG. 6 is a screenshot illustrating an exemplary list of words or phrases available for user feedback in accordance with various embodiments. FIG. 6 illustrates a screenshot illustrating an example of defining a word in accordance with various embodiments. FIG. 6 illustrates a screenshot illustrating an exemplary list of select form responses, according to various embodiments. FIG. 6 is a screenshot illustrating an exemplary list of status for a submitted response in accordance with various embodiments. FIG. 6 illustrates a screenshot illustrating an exemplary incentive notification, according to various embodiments. 6 is a flowchart of a method for detecting unreadable phrases in a language corpus, according to various embodiments. FIG. 6 is a schematic diagram of a fraud detection module according to various embodiments. 4 is a flowchart of a method for detecting fraud in translations provided with incentives, in accordance with various embodiments. FIG. 1 is a schematic diagram of a system for performing speech-to-text transcription and translation in a group chat environment, according to various embodiments. FIG. 6 is a schematic diagram of a chat history module for converting and / or translating a chat history in accordance with various embodiments. 6 is a flowchart of a method for converting and / or translating a chat history, according to various embodiments. FIG. 5 includes a screenshot of a user interface for blocking one or more users in a chat session, according to various embodiments. FIG. 5 includes a screenshot of a user interface for unblocking one or more users of a chat session, according to various embodiments. FIG. 5 includes a flowchart of a method for blocking one or more users in a chat session, according to various embodiments. FIG. 6 includes a screenshot of a user interface that allows a user to modify the language translation of an original message, according to various embodiments. FIG. 6 includes a screenshot of a user interface that allows a user to modify the language translation of an original message, according to various embodiments. FIG. 6 includes a screenshot of a user interface that allows a user to modify the language translation of an original message, according to various embodiments. FIG. 6 includes a screenshot of a user interface that allows a user to modify the language translation of an original message, according to various embodiments. FIG. 6 includes a screenshot of a user interface that allows a user to modify the language translation of an original message, according to various embodiments. FIG. 6 includes a screenshot of a user interface that allows a user to modify the language translation of an original message, according to various embodiments. FIG. 6 includes a screenshot of a user interface that allows a user to determine translation modifications submitted by other users in exchange for possible rewards, according to various embodiments. FIG. 6 includes a screenshot of a user interface that allows a user to determine translation modifications submitted by other users in exchange for possible rewards, according to various embodiments. FIG. 6 is a schematic diagram of a translation accuracy module for assessing translation accuracy, according to various embodiments. 6 is a flowchart of a method for assessing the accuracy of a translation, according to various embodiments.

DETAILED DESCRIPTION The various embodiments described herein relate to multilingual communication and facilitate multilingual communication. Some embodiments of systems and methods include, for example, Internet-based chat (eg, Apple® iMessage®, Windows® Live Messenger, etc.), email (eg, embedded forum messaging, Yahoo (registered), etc. Trademark) mail, RFC 5322, etc.), text-based cellular communications (eg, SMS or MMS messages), posting to online forums (eg, posting to web-based hobby forums), posting to online social media services (eg, Twitter) (Registered trademark), Facebook (registered trademark), etc.) and the like may be possible. Certain embodiments may also be used to translate transcripts of past communications or conversations (eg, accumulated transcripts or chat history). Various embodiments include specialized / domain-related terminology (eg chat terms), abbreviations, acronyms, proper nouns, common nouns, reduced forms, colloquial words or phrases in text, and obscene Communication systems and methods may be implemented that translate text between two or more languages (eg, spoken) while addressing / corresponding to one or more of a typical word or phrase. For example, some systems and methods described herein are utilized in connection with chat systems such as those used in massive multiplayer online (MMO) games that tend to have users chatting in different foreign languages. Can be done. In some embodiments, chat dialogs between two or more users can be translated without being conscious of intervention and presented to each user in their native language or selected language. In addition, through the use of a multi-layer / multi-module conversion process, certain embodiments are faster between two or more users (eg, in their native languages) than are otherwise possible with conventional translation systems alone. ) Communication translation can be facilitated (eg translation in a few microseconds).

  According to some embodiments, the system or method may translate from a chat term in a first language, such as English, to a chat term in a second language, such as French. In another example, the system or method may form a formal language in the first language (eg, English) from a chat term in the first language (eg, English) before attempting to translate into the second language (eg, French). Can be converted into a different way of speaking. Some embodiments may include data stores (eg, translations) that may include translations entered manually by a human operator, or translations based on those previously performed by a translation system (eg, historical translations performed by one embodiment). Such text translation can be realized by first querying the cache. Embodiments convert one or more parts of text to make it more suitable for accurate text translation (eg, chat terms, acronyms, abbreviations, proper nouns, common nouns, colloquials, and base words in the text). May attempt to process one or more of the language. For example, an embodiment may convert a given text to account for (current or past) idiom usage across different languages. Embodiments may attempt to query the data store again after conversion of a portion of text. If this translation lookup retry fails, the embodiment uses a machine translation service (eg, a third party cloud-based translation service such as Google® translation) to convert the text (which may have been translated). You can try to translate

  Embodiments convert one translated formal text into a chat term in a new language (eg, translate a formal French word into a French chat term) and translate the final generated text Further improvements can be attempted. Accordingly, some embodiments provide chat between chat terms in a first language (eg, English) and chat terms in a second language (eg, Russian, French, Spanish, Chinese, Hindi, etc.). Facilitates translation.

  Some embodiments may help reduce or avoid the need to use machine translation (thus reducing time, costs, and other overhead associated with machine translation) and have minimal context Or may facilitate the accurate translation of text containing short text structures. If machine translation is facilitated by a third party service or by a secure network connection (eg, a secure socket layer [SSL] connection), the cost or overhead avoided by an embodiment may be significant.

  As understood herein, “translation” means manipulating a first text segment in a first language to form a second text segment in the first language. . The resulting second text segment may also be referred to herein as “transformed text”. “Translation” will be understood to mean converting a text segment in a first language into a corresponding text segment in a second language.

  Also, as understood herein, a “translated translation” is one that has already been converted according to the embodiments described herein (eg, from the text of a chat term in a first language to a first Means translation of the text segment (converted into formal text in the first language) (from the first language to the second language). “Untranslated translation” means a translation (from a first language to a second language) of a text segment before the text segment is transformed according to embodiments described herein. Will be understood.

  Various embodiments may implement different translation / translation procedures, and certain procedures are well suited for specific translation applications. For example, for a particular chat system application, the conversion procedure implemented is the following set of conversion related modules: chat term module, acronym module, proper noun module, common noun module, colloquial module, spell check module, abbreviation module, And applying obscene language modules in the order listed. In general, the conversion / translation procedure employed will determine which conversion operations are performed, when conversion operations are performed throughout the translation process (eg, conversion is performed before or after machine translation), or in what order. Is determined (for example, the priority or priority of the conversion operation). The translation / translation procedure uses what translations are pre-populated in the data store (for example, translations can be stored in a translation “cache” to speed up the entire process) and when the translation cache is used throughout the translation process It can also be determined. For certain embodiments, the conversion / translation procedure employed can be determined dynamically based on the state of the environment in which the embodiment is used. For example, if the chat system user's burden is heavier than normal, the conversion / translation procedure may be switched to one that reduces the processing burden on the chat system (eg, more dependent on machine translation than on the data store).

  FIG. 1 is a block diagram illustrating an exemplary environment 100 utilizing a multilingual system according to various embodiments. As shown in FIG. 1, a typical environment 100 includes clients 102-1 to 102-N (hereinafter collectively referred to as "clients 102"), a chat server 108, and a translation server 110, each of which is a computer. The networks 106 may be communicatively coupled to each other. In accordance with some embodiments, the computer network 106 is implemented or facilitated using one or more local or wide area communication networks such as the Internet, a WiFi network, a WiMax network, a private network, a public network, etc. Can be Depending on the embodiment, some or all of the communication connections with the computer network 106 may be transferred between various entities shown in the exemplary environment 100 using encryption (eg, secure socket layer [SSL]). The information that is being made can be secure.

  Each of client 102, chat server 108, and translation server 110 may be implemented using one or more digital devices that may be similar to the digital devices described below with reference to FIG. For example, client 102-1 may receive user input (eg, configured for user interaction) and one or more other clients (eg, of clients 102-2 through 102-N). It can be any form of computing device that can provide a client user interface that facilitates communication with any one) and can communicate with the chat server 108 via the computer network 106. Such computing devices are mobile phones, tablet computing devices, laptops, desktop computers, personal digital assistants, portable gaming units, wired gaming units, thin clients, set-top boxes, portable multimedia players, or known to those skilled in the art May include any other type of network accessible user equipment. In addition, one or more of the chat server 108 and translation server 110 may include one or more cloud-based services (eg, System-as-a-Service [SaaS], Platform-as-a-Service [PaaS], or Infrastructure-as- a-Service [IaaS]), or may be composed of one or more servers that may be implemented using one or more cloud-based services.

  Clients 102 may be configured to communicatively connect to a chat server 108 that provides or otherwise facilitates a chat session between clients 102. Each of clients 102-1 through 102-N includes a chat client system (104-1 through 104-N, respectively) that allows a user at each of clients 102 to access a chat session via chat server 108. obtain. In addition, depending on the embodiment, each of chat client systems 104-1 to 104-N (hereinafter collectively referred to as "chat client system 104") is a non-chat application (eg, a video game) as a stand-alone chat application. Can be implemented as a chat function built in or by a chat service accessible at the client via a web browser. One skilled in the art will recognize that for some embodiments, the chat client systems 104 may not be heterogeneous with respect to each other and still be able to establish a chat session between them. Chat client system 104 receives chat input (eg, chat messages) from each user in the language (and corresponding character set) selected by the user (eg, based on the user's preferences or preferences) It may be possible to send chat input to chat server 108 to be relayed to a user (eg, another user in another chat client system). The chat client system 104 receives chat output (eg, a chat session dialog) from the chat server 108 (eg, from another user in another chat client system), and the received chat output is determined by the user (eg, user settings or It may also be possible to display in a selected language (and corresponding character set) (based on preferences).

  Through the use of some embodiments, the translation of the chat dialog may be transparent to the user when the dialog is passed between chat client systems 104. Thus, for some embodiments, all chat dialogs presented in a given chat client system 104 will be independent of which language by the user in other chat client systems 104 that contribute to the same chat dialog, It may be the language specific to (or selected by) the user in that given chat client system 104. For example, if a user in chat client system 104-1 and a user in chat client system 104-2 contribute to the same chat dialog (ie, are involved in the same chat session), in chat client system 104-1 The user may have selected to enter and receive the chat dialog in English, while the user at chat client system 104-2 may have selected to enter and receive the chat dialog in Russian. . Users at client systems 104-1 and 104-2 will see the same chat content, but the chat dialog will be presented in their respective selected language.

  As shown, chat server 108 includes a chat host system 112 configured to establish and / or facilitate a chat session between chat client systems 104 and the various systems and methods described herein. And a communication conversion and translation (CTT) system 114 configured to perform conversion and / or translation operations according to For some embodiments, chat client systems 104 may establish chat sessions with each other via chat host system 112. Chat host system 104 may utilize the functionality of CTT system 114 in facilitating transparent translation of chat dialogs between chat client systems 104. One skilled in the art will recognize that for some embodiments, chat host system 112 and CTT system 114 may be part of separate servers, and the entity that operates chat host system 112 is the entity that operates CTT system 114. You will recognize that they may be different. For example, chat host system 112 may be a third party chat host system that utilizes the services of CTT system 114.

  Also illustrated, the translation server 110 may include a translation module 116 configured to receive a machine text translation request and respond to the request. In accordance with some embodiments, CTT system 114 may utilize the operations / services of translation module 116 in performing machine translation of text. The CTT system 114 may obtain access to services provided by the translation module 116 using one or more translation application programming interfaces (APIs). Depending on the embodiment, the translation module 116 (and the server 110 to which it belongs) may be operated by a third party such as Google® that may provide machine translation services for free or for a fee. Although the translation module 116 is shown as a component that runs on a separate server from the CTT system 114, those skilled in the art will recognize that, for some embodiments, the translation module 116 runs on the same server as the CTT system 114. It will be appreciated that and / or may be an integrated component of the CTT system 114.

  FIG. 2 is a block diagram illustrating an exemplary communication conversion and translation system 114 according to various embodiments. As shown, CTT system 114 includes communication conversion and translation (CTT) control module 202, communication conversion and translation (CTT) communication module 204, language module 206, conversion module 208, translation data store 210, and translation application programming. An interface (API) module 212 may be included. The CTT control module 202 controls and / or adjusts the performance of various operations within the CTT system 114 as the CTT system 114 performs conversion or translation operations according to some systems and methods described herein. Can be configured as follows. For some embodiments, the CTT control module 202 controls the operation of other components of the CTT system 114, such as the CTT communication module 204, language module 206, conversion module 208, translation data store 210, and translation API module 212. obtain.

  CTT communication module 204 may be configured to facilitate communication between CTT system 114 and systems and components outside CTT system 114, such as chat server 108 and / or translation server 110. Thus, via the CTT communication module 204, the CTT system 114 may receive a chat dialog (including one or more chat messages) to be translated or translated by the CTT system 114, and the translated due to the CTT system 114. Can output a chat dialog.

  Language module 206 may be configured to identify one or more languages being used in connection with the chat dialog received by CTT system 114. For some embodiments, the language module 206 identifies the language by analyzing the content of the received chat dialog and / or each chat client system (eg, chat client system) involved in the received chat dialog. 104) language preference / setting information can be obtained.

  The conversion module 208 is configured to perform conversion operations on chat dialogs (including one or more chat messages) received by the CTT system 114 in accordance with some systems and methods described herein. obtain. In accordance with some embodiments, the conversion operations performed by the conversion module 208 may include, but are not limited to, those associated with chat terms, acronyms, abbreviations, proper nouns, common nouns, colloquial words, and obscene language. Additional details of the conversion module 208 are described in FIG.

  The translation data store 210 stores pre-translated text, and then as the CTT system 114 performs translated and untranslated translations according to some systems and methods described herein. It can be configured to provide pre-translated text to the CTT system 114. As described herein, the translation data store 210 may operate as a cache for translations performed in advance by the CTT system 114 and / or by a human operator (eg, via a translation training system). ) Translations entered and stored manually may be stored. For some embodiments, translations may be populated in the translation data store 210 that will speed up the performance of the CTT system 114 for a chat context. For example, if the CTT system 114 is used with a chat system associated with an MMO game, the translations specifically associated with the MMO game (converted and unconverted) are translated into the translation data store 210 (eg, the CTT system). (By 114 operators). For certain embodiments, the multi-layer / multi-module approach to transforming text used by the transform module 208 is particularly well suited for dealing with chat text in MMO games, which tends to be complex in nature.

  Depending on the embodiment, the data store 210 may include untranslated translations (eg <official English> “you” → <official French> “vous”), translated translations (eg <English chat terms> ” u "→ <official French>" vous ") or both. For some embodiments, translation data store 210 may store translations so that corresponding chat messages can be identified using hash values / tags. For example, to store a Spanish translation for the original English message, the Spanish translation may be stored based on the hash value of the English message, thereby converting the Spanish translation to the hash value of the English message. It becomes possible to search and acquire later using. One skilled in the art will recognize that for some embodiments, the translation data store 210 may include a separate data store for translation between two specific languages. Accordingly, when a chat message is being translated / translated between English and French, a corresponding data English-French data store may be utilized for operations associated with the translation data store 210.

  The translation API module 212 may be configured to provide the CTT system 114 with access to machine translation services provided outside the CTT system 114 (eg, by the translation module 116 of the translation server 110). As described herein, the translation API module 212 may be utilized by the CTT system 114 when there is no translation in the translation data store 210.

  FIG. 3 is a block diagram illustrating an exemplary conversion module 208 according to various embodiments. As shown, conversion module 208 includes chat term module 302, acronym module 304, proper noun module 306, common noun module 308, colloquial module 310, spell check module 312, abbreviation module 314, and / or obscenity. Module 316 may be included. According to some embodiments, during operation, conversion module 208 may process chat messages in whole or in part (eg, split the message into tokens or logical parts and then process those tokens / parts). To do). In some embodiments, various modules of the conversion module 208 may be invoked in parallel.

  Chat term module 302 may be configured to identify one or more words or phrases in a chat message associated with chat terminology (i.e., chat terms), and for the identified words or phrases, It may be configured to suggest replacement (eg, corresponding formal / i.e. Not chat terms) words or phrases. In some embodiments, chat term module 302 may identify a word or phrase of the identified chat term so that it is skipped or otherwise ignored during subsequent machine translation (eg, by translation module 116). Can be flagged. In addition, in some embodiments, the words or phrases of the identified chat terms may be flagged for later review and treatment by a human operator (eg, an administrator of CTT system 114). In order to identify a chat term word or phrase and / or its corresponding (formal) word or phrase, some embodiments provide a chat term word or phrase and / or chat term word or phrase and their A data set (e.g., stored on a data store) may be utilized that includes a mapping with the corresponding words and phrases. The dataset may be configured as a training or learning system, may be proprietary (eg, collected “in-house” manually by an administrator of the CTT system 114), or commercially available. Or may be obtained from publicly available Internet knowledge bases. For example, chat term module 302 may employ statistical machine translation in its function. For some embodiments, the employed statistical machine translation uses bilingual text extracted from a transformation that protects context information and / or otherwise adds grammar to non-grammatical sentences, and Training can be done using pairs of phrase levels. The results from the chat term module 302 may be the result of the chat term word or phrase flagged by the chat term module 302 to be ignored, the suggested replacement, or the chat term module 302 (eg, for the identified chat term It may include words or phrases that are not chat terms inserted into the message (instead of words or phrases). Depending on the embodiment, the message originating from the chat term module 302 may be provided to another conversion module (within the conversion module 208) for further processing or converted by the chat term module 302. The proposed replacement may be provided to the CTT control module 202 to determine whether is in the data store 210.

  The acronym module 304 may be configured to identify one or more acronyms in the chat message, and further suggests replacement words or phrases (e.g., represented by acronyms) that correspond to the acronyms. It may be configured as follows. In some embodiments, the acronym module 304 flags the identified acronyms to be skipped or otherwise ignored during subsequent machine translation (eg, by translation module 116). obtain. In addition, in some embodiments, the identified acronyms can be flagged for later review and treatment by a human operator (eg, an administrator of the CTT system 114). In order to identify an acronym and / or its corresponding word or phrase, some embodiments include an acronym and / or a mapping of the acronym to their corresponding word and phrase (eg, on a data store). Data set) can be used. The dataset may be configured as a training or learning system, may be proprietary (eg, collected “in-house” manually by an administrator of the CTT system 114), or commercially available. Or may be obtained from publicly available Internet knowledge bases. The result from the acronym module 304 is an acronym flagged by the acronym module 304 to be ignored, a suggested replacement, or a message by the acronym module 304 (eg, instead of the identified acronym). May include words or phrases inserted into Depending on the embodiment, the message resulting from the acronym module 304 may be provided to another conversion module (within the conversion module 208) for further processing, or the message converted by the acronym module 304. The proposed replacement may be provided to the CTT control module 202 to determine whether is in the data store 210.

  The proper noun module 306 may be configured to identify one or more proper nouns in the chat message and further suggests replacement words or phrases (eg, represented by proper nouns) corresponding to the proper nouns. It may be configured as follows. In some embodiments, the proper noun module 306 flags the identified proper nouns to be skipped or otherwise ignored during subsequent machine translation (eg, by the translation module 116). obtain. In addition, in some embodiments, the identified proper nouns can be flagged for later review and treatment by a human operator (eg, an administrator of the CTT system 114). In order to identify proper nouns and / or their corresponding words or phrases, some embodiments may include proper nouns (eg, well-known proper names such as Disneyland® or common names of individuals), and / or proper nouns. A data set (e.g., stored on a data store) that includes a mapping between and their corresponding words and phrases may be utilized. The dataset may be configured as a training or learning system, may be proprietary (eg, collected “in-house” manually by an administrator of the CTT system 114), or commercially available. Or may be obtained from publicly available Internet knowledge bases. The result from the proper noun module 306 is the message that the proper noun is flagged by the proper noun module 306 to be ignored, the suggested replacement, or the message by the proper noun module 306 (eg, in place of the identified proper noun). May include words or phrases inserted into Depending on the embodiment, the message resulting from the proper noun module 306 may be provided to another conversion module (within the conversion module 208) for further processing, or the message converted by the proper noun module 306. The proposed replacement may be provided to the CTT control module 202 to determine whether is in the data store 210.

  The common noun module 308 may be configured to identify one or more common nouns in the chat message, and further suggests replacement words or phrases that correspond to the common nouns (eg, represented by common nouns). It may be configured as follows. In some embodiments, the common noun module 308 flags the identified common nouns to be skipped or otherwise ignored during subsequent machine translation (eg, by the translation module 116). obtain. In addition, in some embodiments, the identified common nouns can be flagged for later review and treatment by a human operator (eg, an administrator of the CTT system 114). In order to identify common nouns and / or their corresponding words or phrases, some embodiments include common nouns and / or mappings of common nouns and their corresponding words and phrases (eg, on a data store). Data set) can be used. The dataset may be configured as a training or learning system, may be proprietary (eg, collected “in-house” manually by an administrator of the CTT system 114), or commercially available. Or may be obtained from publicly available Internet knowledge bases. The result from the common noun module 308 is the message that the common noun module 308 has flagged to be ignored, the suggested replacement, or the common noun module 308 (eg, instead of the identified common noun). May include words or phrases inserted into Depending on the embodiment, the message resulting from the common noun module 308 may be provided to another conversion module (in the conversion module 208) for further processing, or the message converted by the common noun module 308. The proposed replacement may be provided to the CTT control module 202 to determine whether is in the data store 210.

  The colloquial module 310 may be configured to identify one or more colloquial words or phrases in the chat message, and further includes substitutions for the identified words or phrases (eg, corresponding formal / i.e. It may be configured to suggest words or phrases (non-spoken). In some embodiments, the colloquial module 310 applies the identified colloquial word or phrase to be skipped or otherwise ignored during subsequent machine translation (eg, by the translation module 116). You can set a flag. In addition, in some embodiments, the identified colloquial word or phrase may be flagged for later review and treatment by a human operator (eg, an administrator of CTT system 114). In order to identify colloquial words or phrases and / or their corresponding (formal) words or phrases, some embodiments may include colloquial words or phrases and / or colloquial words or phrases and A data set (e.g., stored on a data store) may be utilized that includes a mapping with the corresponding words and phrases. The dataset may be configured as a training or learning system, may be proprietary (eg, collected “in-house” manually by an administrator of the CTT system 114), or commercially available. Or may be obtained from publicly available Internet knowledge bases. The result from colloquial module 310 is the result of colloquial words or phrases flagged by colloquial module 310 to be ignored, suggested substitutions, or colloquial module 310 (eg, identified colloquial words or phrases (Instead of) may contain non-spoken words or phrases inserted into the message. Depending on the embodiment, the message originating from the spoken module 310 may be provided to another conversion module (within the conversion module 208) for further processing, or the message converted by the spoken module 310 may be stored in the data store. A proposed replacement may be provided to the CTT control module 202 to determine if it is within 210.

  Spell check module 312 may be configured to identify one or more misspelled words or phrases in the chat message, and further replace (eg, corrected) words for the identified words or phrases. Or it may be configured to suggest phrases. For example, the spell check module 312 may be configured to automatically correct a word or phrase to a suggested replacement word or phrase. In some embodiments, the spell check module 312 may identify the misspelled word or phrase that is skipped or otherwise ignored during subsequent machine translation (eg, by the translation module 116). Can be flagged. In addition, in some embodiments, the identified misspelled word or phrase may be flagged for later review and treatment by a human operator (eg, an administrator of CTT system 114). In order to identify a misspelled word or phrase and / or its corresponding (corrected) word or phrase, some embodiments include a misspelled word or phrase and / or a misspelled word or phrase A data set (e.g., stored on a data store) that includes mappings with their corresponding words and phrases may be utilized. The dataset may be configured as a training or learning system, may be proprietary (eg, collected “in-house” manually by an administrator of the CTT system 114), or commercially available. Or may be obtained from publicly available Internet knowledge bases. The result from the spell check module 312 is the result of a misspelled word or phrase flagged by the spell check module 312 to be ignored, a suggested replacement, or a spell check module 312 (eg, a misspelled word or phrase). (Instead of) may contain corrected words or phrases inserted into the message. Depending on the embodiment, the message resulting from the spell check module 312 may be provided to another conversion module (within the conversion module 208) for further processing, or the message converted by the spell check module 312 may be A proposed replacement may be provided to the CTT control module 202 to determine if it is in the data store 210.

  The abbreviation module 314 may be configured to identify one or more abbreviations in the chat message, and is further configured to suggest replacement words or phrases (eg, represented by abbreviations) that correspond to the abbreviations. May be. In some embodiments, the abbreviation module 314 may flag the identified abbreviations to be skipped or otherwise ignored during subsequent machine translation (eg, by the translation module 116). In addition, in some embodiments, the identified abbreviations can be flagged for later review and treatment by a human operator (eg, an administrator of CTT system 114). To identify abbreviations and / or their corresponding words or phrases, some embodiments include abbreviations and / or mappings of abbreviations and their corresponding words and phrases (eg, stored on a data store). A) Data sets can be used. The dataset may be configured as a training or learning system, may be proprietary (eg, collected “in-house” manually by an administrator of the CTT system 114), or commercially available. Or may be obtained from publicly available Internet knowledge bases. The result from the abbreviation module 314 is the abbreviation flagged by the abbreviation module 314 to be ignored, the suggested replacement, or the word inserted into the message (eg, in place of the identified abbreviation) by the abbreviation module 314 Or it may contain phrases. Depending on the embodiment, the message resulting from the abbreviation module 314 may be provided to another conversion module (within the conversion module 208) for further processing, or the message converted by the abbreviation module 314 may be stored in the data store. A proposed replacement may be provided to the CTT control module 202 to determine if it is within 210.

  The obscene language module 316 may be configured to identify one or more obscene words or phrases (hereinafter referred to as “obscene language”) in the chat message, and further supports obscene language May be configured to suggest replacement words or phrases (e.g., suitable alternative words) (e.g., a tone-down fold expression). In some embodiments, the obscene language module 316 flags the identified obscene language so that it may be skipped or otherwise ignored during subsequent machine translation (eg, by translation module 116). Can stand up. In addition, in some embodiments, the identified obscene words can be flagged for later review and treatment by a human operator (eg, an administrator of the CTT system 114). In order to identify obscene words and / or their corresponding words or phrases, some embodiments include mapping of obscene words and / or abbreviations with their corresponding words and phrases (eg, a data store). A data set (stored above) may be used. The dataset may be configured as a training or learning system, may be proprietary (eg, collected “in-house” manually by an administrator of the CTT system 114), or commercially available. Or may be obtained from publicly available Internet knowledge bases. The results from the obscenity module 316 are the obscenity flagged by the obscenity module 316 to be ignored, the proposed replacement, or the obscenity module 316 (eg, the identified obscenity (Instead of) may contain words or phrases inserted into the message. Depending on the embodiment, the message resulting from the obscenity module 316 may be provided to another conversion module (in the conversion module 208) for further processing or converted by the obscenity module 316. A suggested replacement may be provided to the CTT control module 202 to determine if the message is in the data store 210.

  For some embodiments, one or more of the various modules of the conversion module 208 can include one in a chat message by inserting a predetermined character before and / or after the flagged portion. Flags can be set for the above parts. For example, if chat term module 302 flags a word “LOL” that is part of a chat message, chat term module 302 inserts a predetermined character (“_”) before and / or after that word (eg, “_LOL_”), which may indicate that the flagged portion should be ignored by the translation module 116.

  For some embodiments, the conversion module 208 may perform two or more conversion operations in parallel on the initial message, and in response, each of the two or more conversion operations receives a separate response. From there, transformation module 208 may then select one transformed message for further processing (eg, for use in operation 514). Depending on the embodiment, each response may include a flagged text portion, a suggested replacement, or a word or phrase inserted in the initial message. Thereafter, the selected transformed message may be subject to selection priority. The priority of selection can determine which transformed messages are selected for further processing according to which precedent. In some embodiments, the priority selection may depend on which conversion operation is most likely to generate a converted message suitable for subsequent lookup or subsequent machine translation in the translation data store 210). Good. In addition, in some embodiments, the priority of selection may depend on which conversion operation produces the most formal converted message. The priority of selection may depend on the conversion / translation procedure selected by the embodiment.

  Table 1 below shows an example of how the conversion module 208 may process a portion of a chat message in accordance with various embodiments. As shown, the conversion module 208 may process chat messages based on tokens or proxy tokens, and may stop processing for a particular token once the conversion has been performed.

Table 1. Chat Message Processing Example FIG. 4 is a block diagram illustrating an exemplary chat client system 104 according to various embodiments. As shown, chat client system 104 may include a chat client controller 402, a chat client communication module 404, and a chat client graphical user interface (GUI) module 406. The chat client control module 402 controls and / or adjusts the performance of various operations within the chat client system 104 when the chat client system 104 performs chat-related operations (eg, a communication chat dialog with the chat server 108). Can be configured. For some embodiments, chat client control module 402 may control the operation of other components of chat client system 104, including, for example, chat client communication module 404 and chat client GUI module 406.

  Chat client communication module 404 may be configured to facilitate communication between chat client system 104 and systems and components outside chat client system 104, such as chat server 108. Accordingly, the chat client module 404 may cause the chat client system 104 to receive a chat dialog to be presented at the chat client system 104 from the chat server 108 (eg, via the chat client GUI module 406). The chat dialog received from the user may be sent to the chat server at 104 (eg, via chat client GUI module 406).

  Chat client GUI module 406 may be configured to provide a user at chat client system 104 with graphical input / output access to chat sessions with other chat client systems. Thus, for some embodiments, the chat client GUI module 406 may present a client GUI adapted to receive user interaction by the client 102 to a user at the client 102. For some embodiments, chat client GUI module 406 allows chat dialogs (eg, as they are received from chat server 108) to users in their selected language (eg, according to the user's language preferences / settings). Can be configured to present. In addition, chat client GUI module 406 may be configured to receive chat input from a user in a language of the user's selection (eg, according to the user's language preferences / settings). As described herein, the language used to present and receive chat dialogs in chat client system 104 is different from the language used to present and receive chat dialogs in other chat client systems. It may be. The chat client GUI module 406 will be further described with reference to FIG.

  FIG. 5 is a flowchart illustrating an exemplary method 500 for multilingual communication according to various embodiments. As described below, for some embodiments, the method illustrated by method 500 includes chat client system 104-1, chat client system 104-2, CTT system 114 (eg, of chat server 108), and (eg, translation). Operations related to translation module 116 (of server 110) may be performed.

  The method 500 may begin at operation 502 where the language module 204 (of the CTT system 114) has a second chat with a first language being used by the user in a first chat client system (eg, 104-1). A second language used by the user in the client system (eg, 104-2) may be identified. According to some embodiments, language module 204 may identify a first language and a second language by obtaining language preferences / settings from respective chat client systems 104.

  In operation 504, the CTT communication module 204 (of the CTT system 114) may receive an initial message in the first language. In some embodiments, the CTT communication module 204 may receive an initial message from the chat host system 112, which is receiving the initial message from a chat client system (eg, 104-1). Also good.

  At operation 506, the CTT control module 202 (of the CTT system 114) may query the translation data store 210 for a corresponding message in the second language that corresponds to the initial message. In operation 508, the CTT control module 202 may determine whether a corresponding message is found in the translation data store 210. If there is one, at operation 510, the CTT communication module 204 may assist in sending a corresponding message to a second chat client system (eg, chat client system 104-2). In some embodiments, a corresponding message may be sent to chat host system 112. Chat host system 112 may relay the corresponding message to a second chat client system (eg, 104-2). The method 500 can then end.

  If the corresponding message does not exist in the translation data store 210, at operation 512, the conversion module 208 may attempt to convert at least a portion of the initial message into a converted message in the first language. As described herein, messages originating from the conversion module 208 may be converted or may remain intact (eg, when the conversion operation of the conversion module 208 does not apply to the initial message). Good. For some embodiments, the conversion module 208 may perform two or more conversion operations in parallel on the initial message, and in response, each of the two or more conversion operations receives a separate response. From there, transformation module 208 may then select one transformed message for further processing (eg, for use in operation 514). Depending on the embodiment, each response may include a flagged text portion, a suggested replacement, or a word or phrase inserted in the initial message. Thereafter, the selected transformed message may be subject to selection priority. The priority of selection can determine which transformed messages are selected for further processing according to which precedent. In some embodiments, the priority selection may depend on which conversion operation is most likely to generate a converted message suitable for subsequent lookup or subsequent machine translation in the translation data store 210). Good. In addition, in some embodiments, the priority of selection may depend on which conversion operation produces the most formal converted message. The priority of selection may depend on the conversion / translation procedure selected by the embodiment.

  Assuming in operation 514 that conversion module 208 has converted the message, CTT control module 202 (of CTT system 114) translates data store 210 for the corresponding message in the second language that corresponds to the converted message. You can refer to In operation 516, the CTT control module 202 may determine whether a corresponding message is found in the translation data store 210. If there is one, at operation 518, the CTT communication module 204 may assist in sending a corresponding message to a second chat client system (eg, chat client system 104-2). In some embodiments, a corresponding message may be sent to chat host system 112. Chat host system 112 may then relay the corresponding message to a second chat client system (eg, 104-2). The method 500 can then end.

  For some embodiments, if the corresponding message still does not exist in the translation data store 210, at operation 520, the CTT control module 202 may select any of the conversion modules 208 to perform on chat messages that have not yet occurred. It can be determined whether there are additional conversion operations.

  If there are additional conversion operations, method 500 returns to operation 512 to perform additional conversion operations. Depending on the embodiment, the additional conversion operation may include applying a different conversion operation than that already performed on the initial message by the conversion module 208, and the same conversion operation performed may be performed in English. May apply to different parts of the chat message, or some combination thereof. For example, if during the first execution of action 512, conversion module 208 applies an action associated with the chat term to the initial message (and creates a first converted message), a second execution of action 512 During, the conversion module 208 may apply the action associated with the abbreviation to the second converted message. Following the subsequent execution of operation 512, method 500 may proceed to operations 514 and 516, where CTT control module 202 responds in a second language corresponding to the resulting latest transformed message. The translation data store 210 may be queried again for messages to be performed, and the CTT control module 202 may determine whether a corresponding message is found in the translation data store 210. By repeatedly performing conversion and query operations in this manner, an embodiment may be able to find a corresponding message before all available conversion operations are to be performed. Those skilled in the art may understand that for certain embodiments, the conversion and query operations may be performed sequentially, and the query operation (e.g., operation 514) may include all available conversion operations provided by the conversion module 208 in the chat message. It will be recognized that it will only be done after it has been done.

  If the corresponding message does not exist in the translation data store 210 and there is no additional conversion operation (of the conversion module 208), in operation 522 (via the translation API module 212), the translation module 116 It may assist in translating the converted message into a corresponding message in the second language. Thereafter, in operation 524, the CTT communication module 204 may assist in sending a corresponding message to a second chat client system (eg, chat client system 104-2). According to some embodiments, a corresponding message may be sent to chat host system 112. Chat host system 112 may then relay the corresponding message to a second chat client system (eg, 104-2). The method 500 can then end.

  For certain embodiments, conversion module 208 may be utilized to convert a corresponding message to a second language before the corresponding message is sent to chat host system 112. As described herein, further conversion processing may be performed on the corresponding message to further improve the translation for the user in the second chat client system (eg, 104-2). For example, if the initial message includes chat terms in a first language (eg, English), the additional conversion process can add chat terms in the second language to the extent possible.

  Although the method steps described above may be represented and described in a certain order, one of ordinary skill in the art will recognize that the order in which the steps are performed may vary between embodiments. In addition, those skilled in the art will recognize that the components described above with respect to method 500 are merely examples of components used in the method, and that for some embodiments, other components may be utilized in some embodiments. Will do.

  FIG. 6 is a flowchart illustrating an exemplary method 600 for converting communications according to various embodiments. As described below, for some embodiments, method 600 may perform operations associated with conversion module 208 (eg, of CTT system 114).

  The method may begin at operation 602 where an initial message is received by the conversion module 208 for the conversion process. According to some embodiments, the conversion module 208 is after failure to identify a message in the translation data store 210 and possibly in a third party or proprietary translation process (eg, as a cloud-based service). The initial message may be received for translation before the initial message is machine translated by a translation module 116) that may be provided. As described herein, particularly context with minimal text, concise sentence structure, specialized / domain-related terminology (eg chat terms for internet-based chat), abbreviations, acronyms, The conversion module 208 is used in various embodiments to facilitate or otherwise enhance text translation when including colloquial, proper nouns, common nouns, obscene words, or some combination thereof. obtain. Text translations that can exploit the operation of the conversion module 208 include, but are not limited to, conversations (eg, transcripts), offline or online Internet-based chat (eg, instant messaging), and mobile phone messaging (eg, SMS or MMS). It may include translation of the resulting text.

  In operation 604, chat term module 302 may identify one or more words or phrases in the initial message associated with the chat terminology (ie, chat terms), and for the identified words or phrases. Replacement (eg, corresponding formal / ie not chat terms) words or phrases may be suggested. In some embodiments, chat term module 302 may identify a word or phrase of the identified chat term so that it is skipped or otherwise ignored during subsequent machine translation (eg, by translation module 116). Can be flagged. In addition, in some embodiments, the words or phrases of the identified chat terms may be flagged for later review and treatment by a human operator (eg, an administrator of CTT system 114). In order to identify a chat term word or phrase and / or its corresponding (formal) word or phrase, some embodiments provide a chat term word or phrase and / or chat term word or phrase and their A data set (e.g., stored on a data store) may be utilized that includes a mapping with the corresponding words and phrases. The dataset may be configured as a training or learning system, may be proprietary (eg, collected “in-house” manually by an administrator of the CTT system 114), or commercially available. Or may be obtained from publicly available Internet knowledge bases. A message resulting from operation 604 (hereinafter “first intermediate message”) is a chat term word or phrase flagged by chat term module 302 to be ignored, a suggested replacement, or chat term module 302. May include words or phrases that are not chat terms inserted into the initial message (eg, in place of identified chat term words or phrases). In some examples, the first intermediate message may be the same as the initial message (eg, when no replacement is performed by chat term module 302). Depending on the embodiment, the first intermediate message resulting from chat term module 302 may be provided to another conversion module (within conversion module 208) for further processing, or converted by chat term module 302. A suggested replacement may be provided to the CTT control module 202 to determine whether the posted message is in the data store 210. Following operation 604, the first intermediate message may be provided to the next operation of conversion module 208 (eg, operation 606) for processing.

  In operation 606, the acronym module 304 may identify one or more acronyms in the chat message and further suggest replacement words or phrases corresponding to the acronyms (eg, represented by the acronyms). May be. In some embodiments, the acronym module 304 flags the identified acronyms to be skipped or otherwise ignored during subsequent machine translation (eg, by translation module 116). obtain. In addition, in some embodiments, the identified acronyms can be flagged for later review and treatment by a human operator (eg, an administrator of the CTT system 114). In order to identify an acronym and / or its corresponding word or phrase, some embodiments include an acronym and / or a mapping of the acronym to their corresponding word and phrase (eg, on a data store). Data set) can be used. The dataset may be configured as a training or learning system, may be proprietary (eg, collected “in-house” manually by an administrator of the CTT system 114), or commercially available. Or may be obtained from publicly available Internet knowledge bases. A message resulting from action 606 (hereinafter “second intermediate message”) is identified by the acronym, suggested replacement, or acronym module 304 (eg, identified by the acronym module 304 to be ignored). May contain words or phrases inserted into the message (instead of the acronyms made). In some examples, the second intermediate message may be the same as the first intermediate message (eg, when no replacement is performed by the acronym module 304). Depending on the embodiment, the second intermediate message resulting from the acronym module 304 may be provided to another conversion module (within the conversion module 208) for further processing or converted by the acronym module 304. A suggested replacement may be provided to the CTT control module 202 to determine whether the posted message is in the data store 210. Following operation 606, the second intermediate message may be provided to the next operation of conversion module 208 (eg, operation 608) for processing.

  In operation 608, the proper noun module 306 may identify one or more proper nouns in the chat message and further suggest replacement words or phrases (eg, represented by proper nouns) corresponding to the proper nouns. May be. In some embodiments, the proper noun module 306 flags the identified proper nouns to be skipped or otherwise ignored during subsequent machine translation (eg, by the translation module 116). obtain. In addition, in some embodiments, the identified proper nouns can be flagged for later review and treatment by a human operator (eg, an administrator of the CTT system 114). In order to identify proper nouns and / or their corresponding words or phrases, some embodiments may include proper nouns (eg, well-known proper names such as Disneyland® or common names of individuals), and / or proper nouns. A data set (e.g., stored on a data store) that includes a mapping between and their corresponding words and phrases may be utilized. The dataset may be configured as a training or learning system, may be proprietary (eg, collected “in-house” manually by an administrator of the CTT system 114), or commercially available. Or may be obtained from publicly available Internet knowledge bases. A message resulting from operation 608 (hereinafter “third intermediate message”) is identified by the proper noun module, proposed replacement, or proper noun module 306 (eg, identified by the proper noun module 306 to be ignored). It may contain words or phrases inserted into the message (instead of proper nouns). In some examples, the third intermediate message may be the same as the second intermediate message (eg, when no replacement is performed by the proper noun module 306). Depending on the embodiment, the third intermediate message resulting from the proper noun module 306 may be provided to another conversion module (in the conversion module 208) for further processing or by the proper noun module 306. A proposed replacement may be provided to the CTT control module 202 to determine whether the converted message is in the data store 210. Following operation 608, a third intermediate message may be provided to the next operation of conversion module 208 (eg, operation 610) for processing.

  In operation 610, the common noun module 308 may identify one or more common nouns in the chat message and further suggest replacement words or phrases corresponding to the common nouns (eg, represented by common nouns). May be. In some embodiments, the common noun module 308 flags the identified common nouns to be skipped or otherwise ignored during subsequent machine translation (eg, by the translation module 116). obtain. In addition, in some embodiments, the identified common nouns can be flagged for later review and treatment by a human operator (eg, an administrator of the CTT system 114). In order to identify common nouns and / or their corresponding words or phrases, some embodiments include common nouns and / or mappings of common nouns and their corresponding words and phrases (eg, on a data store). Data set) can be used. The dataset may be configured as a training or learning system, may be proprietary (eg, collected “in-house” manually by an administrator of the CTT system 114), or commercially available. Or may be obtained from publicly available Internet knowledge bases. A message resulting from action 610 (hereinafter “fourth intermediate message”) is identified by the common noun, suggested replacement, or common noun module 308 flagged by the common noun module 308 to be ignored (eg, identified). May contain words or phrases inserted into the message (instead of common nouns). In some examples, the fourth intermediate message may be the same as the third intermediate message (eg, when no replacement is performed by the common noun module 308). Depending on the embodiment, the fourth intermediate message resulting from the common noun module 308 may be provided to another conversion module (in the conversion module 208) for further processing, or by the common noun module 308. A proposed replacement may be provided to the CTT control module 202 to determine whether the converted message is in the data store 210. Following operation 610, a fourth intermediate message may be provided to the next operation of conversion module 208 (eg, operation 612) for processing.

  In operation 612, the colloquial module 310 may identify one or more colloquial words or phrases in the chat message and further replaces the identified word or phrase (eg, the corresponding formal / i.e. (Non-spoken) words or phrases may be suggested. In some embodiments, the colloquial module 310 applies the identified colloquial word or phrase to be skipped or otherwise ignored during subsequent machine translation (eg, by the translation module 116). You can set a flag. In addition, in some embodiments, the identified colloquial word or phrase may be flagged for later review and treatment by a human operator (eg, an administrator of CTT system 114). In order to identify colloquial words or phrases and / or their corresponding (formal) words or phrases, some embodiments may include colloquial words or phrases and / or colloquial words or phrases and A data set (e.g., stored on a data store) may be utilized that includes a mapping with the corresponding words and phrases. The dataset may be configured as a training or learning system, may be proprietary (eg, collected “in-house” manually by an administrator of the CTT system 114), or commercially available. Or may be obtained from publicly available Internet knowledge bases. A message resulting from action 612 (hereinafter “fifth intermediate message”) is either spoken word or phrase flagged by the spoken module 310 to be ignored, suggested replacement, or by the spoken module 310 ( It may include non-spoken words or phrases inserted into the message (instead of identified spoken words or phrases, for example). In some examples, the fifth intermediate message may be the same as the fourth intermediate message (eg, when no replacement is performed by colloquial noun module 310). Depending on the embodiment, the fifth intermediate message resulting from the colloquial module 310 may be provided to another conversion module (in the conversion module 208) for further processing or has been converted by the colloquial module 310. A suggested replacement may be provided to the CTT control module 202 to determine if the message is in the data store 210. Following operation 612, a fifth intermediate message may be provided to the next operation of conversion module 208 (eg, operation 614) for processing.

  In operation 614, the spell check module 312 may identify one or more misspelled words or phrases in the chat message and further replace (eg, correct) words for the identified words or phrases. Or you may suggest a phrase. For example, the spell check module 312 may automatically correct the word or phrase with the suggested replacement word or phrase. In some embodiments, the spell check module 312 may identify the misspelled word or phrase that is skipped or otherwise ignored during subsequent machine translation (eg, by the translation module 116). Can be flagged. In addition, in some embodiments, the identified misspelled word or phrase may be flagged for later review and treatment by a human operator (eg, an administrator of CTT system 114). In order to identify a misspelled word or phrase and / or its corresponding (corrected) word or phrase, some embodiments include a misspelled word or phrase and / or a misspelled word or phrase A data set (e.g., stored on a data store) that includes mappings with their corresponding words and phrases may be utilized. The dataset may be configured as a training or learning system, may be proprietary (eg, collected “in-house” manually by an administrator of the CTT system 114), or commercially available. Or may be obtained from publicly available Internet knowledge bases. A message resulting from operation 614 (hereinafter “sixth intermediate message”) is a misspelled word or phrase flagged by spell check module 312 to be ignored, suggested replacement, or spell check module 312. May include corrected words or phrases inserted into the message (eg, in place of misspelled words or phrases). In some examples, the sixth intermediate message may be the same as the fifth intermediate message (eg, when no replacement is performed by the spell check module 312). Depending on the embodiment, the sixth intermediate message resulting from the spell check module 312 may be provided to another conversion module (in the conversion module 208) for further processing or by the spell check module 312. A proposed replacement may be provided to the CTT control module 202 to determine whether the converted message is in the data store 210. Following operation 614, a sixth intermediate message may be provided to the next operation of conversion module 208 (eg, operation 616) for processing.

  In operation 616, the abbreviation module 314 may identify one or more abbreviations in the chat message and may further suggest replacement words or phrases corresponding to the abbreviations (eg, represented by abbreviations). In some embodiments, the abbreviation module 314 may flag the identified abbreviations to be skipped or otherwise ignored during subsequent machine translation (eg, by the translation module 116). In addition, in some embodiments, the identified abbreviations can be flagged for later review and treatment by a human operator (eg, an administrator of CTT system 114). To identify abbreviations and / or their corresponding words or phrases, some embodiments include abbreviations and / or mappings of abbreviations and their corresponding words and phrases (eg, stored on a data store). A) Data sets can be used. The dataset may be configured as a training or learning system, may be proprietary (eg, collected “in-house” manually by an administrator of the CTT system 114), or commercially available. Or may be obtained from publicly available Internet knowledge bases. A message resulting from action 616 (hereinafter “seventh intermediate message”) is abbreviated, suggested replacement, or abbreviation module 314 (eg, identified abbreviation) flagged by abbreviation module 314 to be ignored. (Instead of) may contain words or phrases inserted into the message. In some examples, the seventh intermediate message may be the same as the sixth intermediate message (eg, when no replacement is performed by abbreviation module 314). Depending on the embodiment, the seventh intermediate message resulting from the abbreviation module 314 may be provided to another conversion module (in the conversion module 208) for further processing or has been converted by the abbreviation module 314. A suggested replacement may be provided to the CTT control module 202 to determine if the message is in the data store 210. Following operation 616, a seventh intermediate message may be provided to the next operation of conversion module 208 (eg, operation 618) for processing.

  In act 618, the obscene language module 316 may identify one or more obscene words or phrases (hereinafter referred to as “obscene words”) in the chat message and further respond to the obscene language. A replacement word or phrase (e.g., an appropriate alternative word) (e.g., a toned down fold expression) may be suggested. In some embodiments, the obscene language module 316 flags the identified obscene language so that it may be skipped or otherwise ignored during subsequent machine translation (eg, by translation module 116). Can stand up. In addition, in some embodiments, the identified obscene words can be flagged for later review and treatment by a human operator (eg, an administrator of the CTT system 114). In order to identify obscene words and / or their corresponding words or phrases, some embodiments include mapping of obscene words and / or abbreviations with their corresponding words and phrases (eg, a data store). A data set (stored above) may be used. The dataset may be configured as a training or learning system, may be proprietary (eg, collected “in-house” manually by an administrator of the CTT system 114), or commercially available. Or may be obtained from publicly available Internet knowledge bases. A message resulting from action 618 (hereinafter “eighth intermediate message”) is sent by an obscene word, suggested replacement, or obscene word module 316 flagged by the obscene word module 316 to be ignored. It may include words or phrases inserted into the message (eg, instead of identified obscene words). In some examples, the eighth intermediate message may be the same as the seventh intermediate message (eg, when no replacement is performed by the obscene language module 316). Depending on the embodiment, the eighth intermediate message resulting from the obscene language module 316 may be provided to another translation module (in the transformation module 208) for further processing, or the obscene language module 316. A suggested replacement may be provided to the CTT control module 202 to determine if the message converted by is in the data store 210. Following operation 618, an eighth intermediate message may be provided to the next operation of conversion module 208 for processing. The method 600 may then end.

  In accordance with some embodiments, the message ultimately resulting from the conversion module 208 (eg, the eighth intermediate message resulting from operation 618) may then be used to query the translation data store 210 for the corresponding message. Good. The corresponding message can serve as a translation for the resulting message. Those skilled in the art will recognize that in some examples, messages originating from the conversion module 208 (eg, messages that are subsequently used to query the translation data store 210) have no conversion applied to the initial message (eg, any It will be appreciated that the initial message may have been the same as the received initial message (e.g., at operation 602) if the initial message passed through operations 604-618 (without any transformation applied).

  Those skilled in the art will also recognize that various embodiments may perform more or less operations than illustrated, may perform different operations than illustrated, and may operate in different orders. Will. In general, the type of conversion operations performed and the order in which they are performed may depend on the conversion procedure employed by the embodiment. As noted herein, various embodiments may implement different conversion / translation procedures in implementing each conversion. Certain procedures are well suited for a particular translation application or translation context. The conversion / translation procedure employed may determine which conversion operations are performed, when the conversion operations are performed, and in what order the conversion operations are performed. The conversion / translation procedure may determine what translations are populated in the translation data store and when the translation data store is utilized during the entire conversion / translation process.

  For some embodiments, intermediate messages resulting from operations in method 600 may have an impact and / or cascading effect on messages resulting from subsequent operations in method 600. In addition, for some embodiments, when a chat message is processed by method 600, each operation of flowchart 600 may be performed on the chat message before the method ends. Alternatively, for some embodiments, the method of flowchart 600 ends early by performing only a subset of the illustrated actions (eg, after at least one action has resulted in a chat message conversion). obtain. According to some embodiments, execution of each operation of flowchart 500 is followed by a query to translation data store 210 for the corresponding message in the desired language based on the resulting latest translated message. obtain. If a corresponding message is identified, the method of flowchart 500 may end early.

  For various embodiments, the method 600 may perform the operations 604-612 in parallel. For example, the CTT control module 202 may perform two or more operations 604-612 in parallel with the initial message and receive a separate response from each of those two or more operations. Each response may include a flagged text portion, a suggested replacement, or a word or phrase inserted into the initial message. Thereafter, the CTT control module 202 may optionally follow (e.g., determine which transformed messages are selected for further processing and according to what precedent) according to the priority of selection. One of the received responses may be selected for processing (eg, querying translation data store 210 or translation by translation module 116).

  For example, during the method 600, the CTT control module 202 may perform an operation 604 for identifying chat term processing, an operation 610 for common noun processing, and an operation 616 for abbreviation processing on the initial message. . In response, operation 604 may return an initial message converted for the chat term. Operation 610 may return the original initial message. Act 616 may return an initial message converted for the abbreviation. Thereafter, based on the priority of selection, the CTT control module 202 may select the transformed message returned from operation 616 for further processing.

  For certain embodiments, a time limit is enforced for performing various operations of method 600. The time limit may cause the conversion operation of method 600 to stop executing if no response / result is received before the time limit expires. In so doing, various embodiments may ensure that certain conversion operations do not unnecessarily interfere with the entire translation / translation process.

  Although the method steps described above may be represented and described in a certain order, one of ordinary skill in the art will recognize that the order in which the steps are performed may vary between embodiments. In addition, those skilled in the art will appreciate that the components described above with respect to the method of flowchart 600 are merely examples of components that may be used in the method, and for some embodiments, other components may be utilized in some embodiments. You will recognize that.

  FIG. 7 is a diagram 700 illustrating an exemplary multilingual chat session between chat client systems 104 (eg, 104-1 and 104-2), according to various embodiments. As shown, chat client system 104-1 may include a chat client GUI module 406-1. Chat client system 104-2 may include chat client GUI module 406-2. As described herein, each of chat client GUI modules 406-1 and 406-2 provides graphical input / output access to chat sessions shared between them, as chat client system 104-1. And 104-2, respectively, may be configured to provide to users. For some embodiments, chat client GUI modules 406-1 and 406-2 may present to each user a client GUI that is adapted to receive user interactions regarding sent and received chat dialogs.

  When the chat dialog 712 (represented by a double arrow in FIG. 7) is passed between the chat client systems 104-1 and 104-2, the chat client GUI modules 406-1 and 406-2 may each have their respective chat clients. Chat dialog 712 may be presented in a language selected (implicitly or explicitly) by a user in system 104-1 or 104-2. As shown, chat client GUI module 406-1 presents chat dialog 712 in output language 708 in a first language (eg, English) and chat input in the first language in second region 710. A chat dialog box 702 configured to receive at may be included. Chat client GUI module 406-2 is configured to present chat dialog 712 in an output area 720 in a second language (eg, French) and receive chat input in the second language in second area 722. Chat dialog box 714 may be included. For some embodiments, when the chat dialog 712 is presented in the dialog boxes 702 and 714, it may include a presentation of a username (eg, a user online identifier) associated with the user entering the chat message in the chat dialog 712.

  In the illustrated embodiment of FIG. 7, the language selected for chat client system 104-1 is English, and the language selected for chat client system 104-2 is French. Accordingly, chat messages 704 ("LOL") and 706 ("Who u laughin at?") Are presented in English in dialog box 702 of chat client GUI module 406-1, while corresponding chat messages 716 ("MDR" ") And 718 (" Quite fair rire? ") Are presented in French in dialog box 714 of chat client GUI module 406-2. Translation of chat messages 704, 706, 716, and 718 may be facilitated by various systems and methods described herein. The translation of messages similar to chat messages 704, 706, 716, and 718 will be further described with reference to FIGS.

  FIG. 8 is a flowchart illustrating the operation of an exemplary multilingual communication method 800 according to various embodiments. As described below, for some embodiments, method 800 may perform operations associated with chat client system 104-1, chat client system 104-2, and CTT system 114 (eg, of chart server 108). In particular, FIG. 8 illustrates the translation of an English chat message containing the text “LOL” into a French chat message, according to some embodiments. In such a situation, the language used by the user in the first chat client system 104-1 is English, and the language used by the user in the second chat client system 104-2 is French. Can occur. According to some embodiments, CTT system 114 may automatically detect these language preferences / preferences for chat client systems 104-1 and 104-2.

  As shown, in operation 802, the first chat client system 104-1 sends an English message for transmission (eg, via the chat host system 112) to the second chat client system 104-2. Can be sent. English messages may be sent to the CTT control module 202 of the CTT system 114 for translation processing.

  In operation 804, the CTT control module 202 may query the translation data store 210 for chat messages that correspond to English chat messages (“LOL”) and have been previously translated into French. In response, at operation 806, translation data store 210 may return a corresponding French message (“MDR”) corresponding to the English chat message (“LOL”) to CTT control module 202. Thereafter, in operation 808, the CTT control module 202 may assist in transmitting the corresponding French chat message ("MDR") to the second chat client system 104-2 (eg, the CTT system 114 may Therefore, a corresponding French chat message is sent to the chat host system 112).

  FIG. 9 is a flowchart illustrating the operation of an exemplary multilingual communication method 900 according to various embodiments. As described below, for some embodiments, the method illustrated by flowchart 900 includes chat client system 104-1, chat client system 104-2, CTT system 114 (eg, of chart server 108), and (eg, translation). Operations related to translation module 116 (of server 110) may be performed. In particular, FIG. 9 illustrates the translation of an English chat message containing the text “LOL” into a French equivalent chat message, according to some embodiments. Unlike the illustrated embodiment of FIG. 8, FIG. 9 illustrates the use of conversion module 208 and translation module 116 (eg, of CTT system 114).

  As shown, in operation 902, the first chat client system 104-1 may transmit a transmission (eg, via the chat host system 112) to a second chat client system 104-2 having a French speaking user. In order to send an English chat message. The English chat message may be sent to the CTT control module 202 of the CTT system 114 for translation processing.

  At operation 904, the CTT control module 202 may query the translation data store 210 for the French equivalent chat message corresponding to the English chat message (“LOL”). In response, at operation 906, the translation data store 210 returns a query failure to the CTT control module 202 so that the translation data store 210 has a corresponding French chat message for the English chat message ("LOL"). It may indicate that it is not. In such cases, at operation 908, the CTT control module 202 may send an English chat message to the conversion module 208 for the conversion process according to an embodiment. As described herein, conversion module 208 may include a plurality of conversion related modules 932 configured to convert chat messages into suitable messages for further translation processing.

  At act 910, the chat term module 302 of the conversion module 208 may convert the English chat message (“LOL”) into a converted English chat message (“laugh out loud”) for conversion for further processing. The communicated English chat message may be returned to the CTT control module 202. Those skilled in the art will recognize that for some embodiments, the English chat message may be processed by an additional module of the conversion module 208 before the converted English chat message is returned to the CTT control module 202. Let's go.

  At operation 912, the CTT control module 202 may query the translation data store 210 for the French equivalent chat message corresponding to the translated English chat message (“laugh out loud”). In response, at operation 914, the translation data store 210 returns a query failure to the CTT control module 202 to translate the corresponding French chat message for the translated English chat message ("laugh out loud"). It may indicate that the data store 210 does not have. In such cases, at operation 916, the CTT control module 202 may send the translated English chat message to the translation module 116 for machine translation processing according to an embodiment.

  At operation 918, translation module 116 may return a machine translated French chat message (“mort de rire”) corresponding to the translated English chat message. The resulting machine translated French chat message (“mort de rire”) is an example of a translated translation of the English chat term chat message (“LOL”).

  In operation 920, the CTT control module 202 converts the machine translated French chat message (“mort de rire”) into a conversion module 208 for further conversion processing of the machine translated French chat message according to an embodiment. Can be sent to. As noted herein, machine translated text may be sent for further conversion processing to further improve the French translation. For example, if the original English chat message contained English chat terms, additional conversion processing can add French chat terms to the extent possible. Accordingly, at act 922, the chat term module 302 of the conversion module 208 may convert the machine translated French chat message (“mort de rire”) into a converted French chat message (“MDR”). The translated French chat message may be returned to the CTT control module 202 for further processing.

  Finally, at operation 924, the CTT control module 202 may assist in transmitting a corresponding French chat message (“MDR”) to the second chat client system 104-2 (eg, the CTT system 114 may A corresponding French chat message is sent to chat host system 112 for transmission). In addition, at operation 926, the CTT control module 202 translates a translation mapping of the translated translation between the original English chat message (“LOL”) and the translated French chat message (“MDR”). It can be stored in the data store 210. Once the mapping is stored in the translation data store 210, it can be used to store translation entries to speed up future translations, for example as illustrated in FIG. As noted herein, translation data store 210 may store a mapping of translated and untranslated translations.

  For some embodiments, the CTT control module 202 may also store corresponding (translated and untranslated) translation mappings determined during operation of the method 900. For certain embodiments, translation mappings may include chat messages that were not originally in translation data store 210 (eg, chat messages shown for action 904 and chat messages shown for action 912) and translation data store 210 lookups. May be between corresponding messages determined during subsequent operations (e.g., a query for translation data store 210 that does not return results via translation module 208 and / or translation module 116 and a decision after query). Mapping between corresponding chat messages).

  For example, as shown in FIG. 9, the CTT control module 202 may generate an initial English chat message (“LOL” in operation 904 and a translated English chat message in operation 912 (“laugh out loud”) (both Both from the translation data store 210 will query the translation data store 210 (in operation 906 and 914, respectively). However, at act 916, the CTT control module 202 ultimately sends the translated English message (“laugh out loud”) to the machine translation module 116 for machine translation, and in response, at act 918. Receive machine translated French chat messages ("mort de rire"). Accordingly, in operation 928, the CTT control module 202 translates the translated translation between the original English chat message ("LOL") and the machine translated French chat message ("mort de rire"). May be stored in the translation data store 210. Similarly, at operation 930, the CTT control module 202 translates between the translated English chat message (“laugh out loud”) and the machine translated French chat message (“mort de rire”). A translation mapping of the translation may be stored in the translation data store 210. In doing so, the method 900 then queries the translation data store 210 for the original English chat message (“LOL”) or the translated English chat message (“laugh out loud”), and the translation data store 210 responds accordingly. Will provide translated translations.

  FIG. 10 is a flowchart illustrating the operation of an exemplary multilingual communication method 1000 according to various embodiments. As described below, for some embodiments, method 1000 includes chat client system 104-1, chat client system 104-2, CTT system 114 (eg, of chart server 108), and translation (eg, of translation server 110). Operations associated with module 116 may be performed. In particular, FIG. 10 illustrates the translation of an English chat message containing the text “Who u laughin at?” Into a French chat message, according to some embodiments.

  As shown, in operation 1002, the first chat client system 104-1 sends an English chat message for transmission (eg, via the chat host system 112) to the second chat client system 104-2. Can be sent. The English chat message may be sent to the CTT control module 202 of the CTT system 114 for translation processing.

  In operation 1004, the CTT control module 202 may query the translation data store 210 for a French equivalent chat message corresponding to an English chat message (Who laughin at?). In response, at operation 1006, the translation data store 210 returns a query failure to the CTT control module 202 and sends the corresponding French chat message for the English chat message (Who u laughin at?) To the translation data store 210. May not be present. In such cases, at operation 1008, the CTT control module 202 may send an English chat message to the conversion module 208 for the conversion process according to an embodiment. As described herein, conversion module 208 may include a plurality of conversion related modules 1036 configured to convert chat messages into suitable messages for further translation processing.

  In act 1010, the chat term module 302 of the conversion module 208 converts the English chat message (Who u laughin at?) Into a converted English chat message (Who you laughin at?), And the converted English chat. The message may be passed to an additional module of conversion module 208 for further processing, such as spell check module 312.

  As described herein, the various modules of the conversion module 208, including the chat term module 302, identify one or more words or phrases in the chat message and replace for the identified words or phrases. It can be configured to suggest words or phrases. Accordingly, those skilled in the art will recognize that, for some embodiments, the conversion performed / proposed by the module of the conversion module 208 may involve word-to-phrase conversion or phrase-to-phrase conversion of chat messages. Will do. For example, at act 1010, chat term module 302 suggests replacing / replacement of the phrase “who u” with “who are you”, possibly during conversion (then the word “laughin” is replaced by “laughing”. To replace the English chat message ("Who u laughin at?") With the converted English chat message ("Who are you laughing at?") Can do. In doing so, the various modules of the conversion module 208, such as the chat term module 302, may improve the grammar for each conversion, possibly eliminating the need for separate modules in the conversion module 208 to achieve grammar improvements. Can bring

  For some embodiments, the chat term module 302 passes the converted English chat message to the CTT control module 202 at operation 1010 before the converted English chat message is passed to an additional module of the conversion module 208. obtain. The CTT control module 202 may then query the translation data store 210 (at operation 1012) for the French equivalent chat message corresponding to the translated English chat message ("Who you laughin at?"). In response, at operation 1014, the translation data store 210 returns a query failure to the CTT control module 202 and the corresponding French chat message for the translated English chat message ("Who you laughin at?"). May not be included in the translation data store 210.

  At operation 1016, the spell check module 312 may perform a spell check process at operation 1018 on the converted English chat message ("Who you laughin at?"). During the spell check process, the spell check module 312 may correct the converted English chat message to a corrected English chat message (“Who you laughing at?”), And the corrected English chat message. May be returned to the CTT control module 202. One skilled in the art will recognize that, for some embodiments, the corrected English chat message may be processed by an additional module of the conversion module 208 before the converted English chat message is returned to the CTT control module 202. You will recognize.

  At operation 1020, the CTT control module 202 may query the translation data store 210 for a French equivalent chat message corresponding to the corrected English chat message (“Who you laughing at?”). In response, at operation 1022, the translation data store 210 returns a query failure to the CTT control module 202 and the corresponding French chat message for the corrected English chat message ("Who you laughing at?"). May not be included in the translation data store 210. In such cases, at operation 1024, the CTT control module 202 may send a corrected English chat message to the translation module 116 for machine translation processing according to an embodiment.

  At operation 1026, translation module 116 may return a machine translated French chat message (“Quite fait rire?”) Corresponding to the corrected English chat message. In operation 1028, the CTT control module 202 converts the machine translated French chat message (“Quite fait rire?”) For further conversion processing of the machine translated French chat message according to an embodiment. May be transmitted to module 208.

  As noted herein, the machine translated text may be sent for further conversion processing to further improve the translation of the text. For example, if the original English chat message contained English chat terms, additional conversion processing can add French chat terms to the extent possible. In operation 1030, the conversion module 208 may return an unmodified machine translated French chat message (“Quite fait rire?”) To the CTT control module 202 for further processing (eg, modules of the conversion module 208). If you don't apply any changes to French chat messages that are machine translated.)

  In operation 1032, the CTT control module 202 may assist in transmitting the machine translated French chat message (“Quite fait rire?”) To the second chat client system 104-2 (eg, the CTT system 114). Sends a corresponding French chat message to chat host system 112 for transmission). In addition, at operation 1034, the CTT control module 202 translates between the original English chat message (“Who u laughin at?”) And the translated French chat message (“Quite fait rire?”). The mapping may be stored in the translation data store 210. As described herein, in an additional operation (not shown), the CTT control module 202 includes previously failed queries for the translation data store 210 and corresponding messages determined after those queries. The corresponding translation mapping based may also be stored in the translation data store 210 (eg, similar to operations 928 and 930 of FIG. 9).

  According to some embodiments, the conversion operations performed by the conversion module 208 may include performing certain conversion operations in parallel, and may perform certain conversion operations sequentially. The order in which the conversion operations are performed in parallel and sequentially may vary between various embodiments. As described herein, if the conversion operations are performed in parallel, some embodiments may select options that determine which converted messages are selected according to which precedent for further processing. Priorities can be adopted.

  FIG. 11 is a flowchart illustrating the operation of an exemplary multilingual communication method 1100 according to various embodiments. As described below, for some embodiments, method 1100 includes chat client system 104-1, chat client system 104-2, CTT system 114 (eg, of chart server 108), and translation (eg, of translation server 110). Operations associated with module 116 may be performed. In particular, FIG. 11 illustrates the translation of an English chat message containing the text “Who u laughin at?” Into a French chat message with parallel translation operations, according to some embodiments.

  As shown, in operation 1102, the first chat client system 104-1 sends an English chat message for transmission (eg, via chat host system 112) to the second chat client system 104-2. Can be sent. The English chat message may be sent to the CTT control module 202 of the CTT system 114 for translation processing.

  In operation 1104, the CTT control module 202 may query the translation data store 210 for the French equivalent chat message corresponding to the English chat message (Who u laughin at?). In response, at operation 1106, the translation data store 210 returns a query failure to the CTT control module 202 and sends the corresponding French chat message for the English chat message (Who u laughin at?) To the translation data store 210. May not be present.

  In such a case, the CTT control module 202 may send an English chat message according to an embodiment to the conversion module 208 for the conversion process. As described herein, conversion module 208 may include a plurality of conversion related modules 1130 configured to convert chat messages into suitable messages for further translation processing. As shown in FIG. 11, during operation 1108, the CTT control module 202 sends an English chat message (“Who u laughin at?”) To two or more conversion related modules 1130 of the conversion module 208 in parallel. Can do. In addition, during operation 1108, the CTT control module 202 may receive the results from the transformation related module 1130 in parallel and send a query to the translation data store 210 in parallel based on the transformation results.

  Accordingly, in operation 1110a, the CTT control module 202 may send an English chat message ("Who u laughin at?") To the chat term module 302 for conversion processing. In parallel, in operation 1110b, the CTT control module 202 may send an English chat message ("Who u laughin at?") To the spell check module 312 for the conversion process. Thereafter, the CTT control module 202 may receive a first translated English chat message (“Who you laughin at?”) From the chat term module 302 in operation 1112a, while in operation 1112b, the CTT control module 202 A second translated English chat message (“Who u laughin at?”) May be received from the spell check module 312. Depending on the respective conversion processing time, the chat term module 302, spell check module 312 and other conversion related modules 1130 may respond to the CTT control module 202 sequentially or in parallel with each other.

  Thereafter, in operation 1114a, the CTT control module 202 may query the translation data store 210 for the French equivalent chat message corresponding to the first translated English chat message ("Who you laughin at?"). In operation 1114b, the CTT control module 202 may query the translation data store 210 for the French equivalent chat message corresponding to the second translated English chat message ("Who u laughing at?"). For some embodiments, during operations 1114a and 1114b, the CTT control module 202 may query the translation data store 210 sequentially or in parallel. In some embodiments, the timing of the query may depend on when the transformation related module 1130 of the transformation module 208 returns the respective response. As shown in FIG. 11, translation data store 210 may return a query failure (eg, <failure>) for the query in operations 1116a and 1116b.

  Ultimately, the CTT control module 202 may select one transformed message from two or more messages resulting from the concurrent operation 1108 for further processing. If only one of the transformation related modules 1130 results in a transformed message, the CTT control module 202 may select that particular transformed message for further processing. As noted herein, the CTT control module 202 may select the converted message based on the priority of selection. The priority of selection may be determined according to the conversion / translation procedure selected by the embodiment. For some embodiments, the priority of selection is whether the converted message has the most formal content, the converted message has the most conversions, or the conversion message is suitable for machine translation. Based on whether it is due to a transformation related module known to be likely to generate

  Once the translated message is selected, at operation 1118, the CTT control module 202 may send the translated English chat message to the translation module 116 for machine translation processing according to an embodiment. For example, as shown in FIG. 11, the CTT control module 202 sends a first translated English chat message (“Who you laughin at?” Generated by the chat term module 302 for transmission to the translation module 116. ") May be selected.

  In operation 1120, the translation module 116 (although it includes the misspelled word “laughin”), the machine translated French chat message (“Quite fait” corresponding to the first translated English chat message). rire? "). In operation 1122, the CTT control module 202 converts the machine translated French chat message (“Quite fait rire?”) For further conversion processing of the machine translated French chat message according to an embodiment. May be transmitted to module 208.

  As noted herein, the machine translated text may be sent for further conversion processing to further improve the translation of the text. For example, if the original English chat message contained English chat terms, additional conversion processing can add French chat terms to the extent possible. At operation 1124, the conversion module 208 may return an unmodified machine translated French chat message (“Quite fait rire?”) To the CTT control module 202 for further processing (eg, If the module does not apply any changes to the French-translated chat message).

  In operation 1126, the CTT control module 202 may assist in transmitting the machine translated French chat message (“Quite fait rire?”) To the second chat client system 104-2 (eg, the CTT system 114). Sends a corresponding French chat message to chat host system 112 for transmission). In addition, in operation 1128, the CTT control module 202 translates between the original English chat message ("Who u laughin at?") And the translated French chat message ("Quite fait rire?"). The mapping may be stored in the translation data store 210. As described herein, in an additional operation (not shown), the CTT control module 202 includes previously failed queries for the translation data store 210 and corresponding messages determined after those queries. The corresponding translation mapping based may also be stored in the translation data store 210 (eg, similar to operations 928 and 930 of FIG. 9).

  For some embodiments, the conversion operations may be performed in a hybrid series / parallel arrangement, whereby some conversion operations are performed in parallel and other conversion operations are performed sequentially. For example, as shown in FIG. 11, an English chat message (“Who u laughin at?”) Is sent concurrently to chat term module 302 and spell check module 312 in operations 1110a and 1110b. Thereafter, once one of the resulting converted messages is selected (eg, based on the priority of selection), other conversion related modules 1130 (eg, acronym module 304, proper noun module, etc.) of conversion module 208 are selected. 306 and the common noun module 308) may operate in parallel on the selected transformed message.

  FIG. 12 is a block diagram of an exemplary digital device 1200. Digital device 1200 includes a processor 1202, a memory system 1204, a storage system 1206, a communication network interface 1208, an I / O interface 1210, and a display interface 1212 communicatively coupled to a bus 1214. The processor 1202 is configured to execute executable instructions (eg, a program). In some embodiments, the processor 1202 includes circuitry or any processor capable of processing executable instructions.

  The memory system 1204 is any memory configured to store data. Some examples of the memory system 1204 are storage devices such as RAM or ROM. The memory system 1204 can include a ram cache. In various embodiments, data is stored in the memory system 1204. Data in the memory system 1204 may be cleared or eventually moved to the storage system 1206.

  Storage system 1206 is any storage device that is configured to retrieve and store data. Some examples of storage system 1206 are flash drives, hard drives, optical drives, and / or magnetic tape. In some embodiments, the digital device 1200 includes a memory system 1204 in the form of RAM and a storage system 1206 in the form of flash data. Both memory system 1204 and storage system 1206 include computer readable media that may store instructions or programs executable by a computer processor including processor 1202.

  A communication network interface (com. Network interface) 1208 may be coupled to a network (eg, computer network 106) via a link 1216. The communication network interface 1208 may support communication via, for example, an Ethernet connection, a serial connection, a parallel connection, or an ATA connection. The communication network interface 1208 may also support wireless communication (eg, 802.11a / b / g / n, WiMax®). It will be apparent to those skilled in the art that the communication network interface 1208 can support many wired and wireless standards.

  Optional input / output (I / O) interface 1210 is any device that receives input from a user and outputs data. Optional display interface 1212 is any device configured to output graphics and data to a display. In one example, the display interface 1212 is a graphics adapter.

  Those skilled in the art will recognize that the hardware elements of the digital device 1200 are not limited to those represented in FIG. Digital device 1200 may include more or fewer hardware elements than those shown. Further, hardware elements share functionality and may still be within the various embodiments described herein. In one example, encoding and / or decoding may be performed by a processor 1202 and / or a coprocessor located on a GPU (ie, Nvidia®).

  The functions and components described above can be comprised of instructions that are stored on a recording medium such as a computer readable medium. The instructions can be retrieved and executed by the processor. Some examples of instructions are software, program code, and firmware. Some examples of recording media are memory devices, tapes, disks, integrated circuits, and servers. The instructions, when executed by the processor, are operable to direct the processor to operate consistent with some embodiments. Those skilled in the art are familiar with instructions, processors, and recording media.

  Various embodiments are described herein by way of example. It will be apparent to those skilled in the art that various modifications can be made and other embodiments can be used without departing from the broader scope of the invention presented herein. These and other variations on the exemplary embodiments are intended to be encompassed by the present invention.

  FIG. 13 is a block diagram illustrating an exemplary user feedback system according to various embodiments. For exemplary purposes, in FIG. 13, an exemplary system for user feedback is shown as part of an exemplary communication translation and translation (CTT) system 1300 according to various embodiments. For example, typical user feedback systems are part of the chat translation system employed by various multilingual chat systems, including game chat systems available in connection with MMO games (eg, in-game chat systems). obtain. Through the use of a typical user feedback system, various players in an MMO game can use a word or flag that is flagged in return for in-game currency / credit / items as an incentive for feedback / approved feedback. The phrase may be selected to provide user feedback, for example through an in-game chat system. Those skilled in the art will appreciate that for some embodiments, some or all of the exemplary user feedback system and its associated components may be separate and / or independent of the exemplary communication conversion and translation system 1300. Will recognize.

  As used herein, it is understood that “feedback” refers to “user feedback” or “user feedback response”, in response to a query that may request feedback on conversion or translation, as the case may be. Should be. Further, it should be understood that the user feedback may include user feedback for conversion or user feedback for translation. User feedback may include a definition for a given word or phrase. The definition allows (i) a given word or phrase to be converted from a given word or phrase in the first language to a corresponding word or phrase in the (same) first language ( ii) allows a given word or phrase to be converted from a given word or phrase in a first language to a corresponding word or phrase in a (different) second language, thereby Perform translated translations and / or (iii) allow a given word or phrase to be translated from a first language to a second language, thereby translating a non-translated word or phrase Execute. As described herein, a user feedback response may be received in response to a query requesting user feedback in connection with a translation failure.

  As used herein, “translation failure” or “translation failure” refers to the actual failure of the translation of the text (eg, the translated text is identical to the original text) or potential A text translation that is flagged as containing a translation failure (for example, if you are reading translated text and the translated text is questionable or the translated text is incorrect) It is understood that it includes a text translation flagged by a user who believes it contains.

  As shown in FIG. 13, the CTT system 1300 includes a communication conversion and translation (CTT) control module 1302, a communication conversion and translation (CTT) communication module 1304, a language module 1306, a conversion module 1308, and a translation data store. 1310 and a translation application programming interface (API) module 1312. In some embodiments, the CTT control module 1302, the CTT communication module 1304, the language module 1306, the conversion module 1308, the translation data store 1310, and the translation API module 1312 are described in the CTT system 114 as described herein. It can be similar to a component.

  As further shown in FIG. 13, the CTT system 1300 includes a translation failure management module 1314, a user feedback (UF) query generation module 1316, a user feedback (UF) query audience selection module 1318, and a query / response value module. 1320, a query application program interface (API) module 1322, a response evaluation module 1324, a translation data store update module 1326, an audience suitability evaluation module 1328, and an incentive reward module 1330.

  The translation failure management module 1314 may be configured to facilitate management of translation failures (eg, failure to translate text from a first language to a second language). For some embodiments, the translation failure management module 1314 allows the system 1300 to use a second language during a chat session from a first user using the first language during the chat session. In attempting to translate a chat message sent to a second user, the CTT system 1300 may be adapted to handle one or more translation failures that may be experienced. As described herein, the text translated by the CTT system 1300 may be a chat message that may include chat terms, abbreviations, colloquials, idioms, and the like. During the conversion or translation of chat messages, some or all of the chat messages may fail to translate because the CTT system 1300 translates and / or translates the parts that cause those failures in the chat message. It will be understood that there may be cases where it cannot be done.

  The functionality provided by the translation failure management module 1314 includes automatically detecting when a text translation failure has occurred, and automatically detecting when a word or phrase in the text cannot be translated. , Including actual or potential translation errors after the translation process, allowing users to flag some or all of the “translated” text, and various audience members Managing which translation failures are selected for user feedback from (e.g. chat members such as players using an in-game chat system) and which words or phrases associated with the translation failure (e.g. How often in the text to be translated Managing which word is selected (based on whether it appears / used) and when the translation failure is no longer a candidate for selection for user feedback (eg, the word or phrase associated with the translation failure) Managed to be removed from the selection pool), but not limited to.

  In various embodiments, the translation failure management module 1314 may manage the overall availability of words or phrases for user feedback by audience members. As used herein, “user feedback opportunities” may include words or phrases that are available for user feedback by audience members. The translation failure management module 1314 may include one or more based on various conditions such as availability of computing resources for user feedback, incentives given in connection with user feedback, quality of feedback responses received in the past, etc. The availability of user feedback opportunities may be suppressed or suspended. For example, continuing to provide incentives (eg, in-game currency or in-game items) to an approved user feedback response can negatively impact the economy (eg, in-game economy) associated with that incentive. It may be judged. Thus, some embodiments may (temporarily) stop the availability of user feedback opportunities that provide incentives, or the current incentive strategy is detrimental to the target economy (eg, in-game economy) And those embodiments may detect an incentive (eg, amount of incentive or type of incentive) that is given for the user feedback opportunity.

  As described herein, an audience member for whom user feedback is sought may be a member who has volunteered to submit such feedback and / or submitted as a participant in a user feedback program. A member who volunteered to provide such feedback in return for incentives when feedback is approved (eg, correct, accepted, or useful in defining a transformation or translation). For some embodiments, the user feedback system described herein provides audience members with user feedback opportunities for incentives (eg, in-game currency or in-game items) that may be useful in a gaming system. It may be part of a gaming system such as an online MMO game that is a game player that chooses to participate in another manner. In this way, the user feedback system can be presented as a game function that a game audience member considers to be a “game” that is “played” for reward, thereby leveraging competition inherent in the gaming environment. . More regarding the selection of audience members is described with respect to the UF query audience selection module 1318.

  As described herein, a communication system user may flag words or phrases that are believed to prevent translation of communicated text or cause inaccurate translation. For example, in a multilingual multi-user chat system associated with an online game, the game player may flag all received chat messages as potentially having translation problems or failures, or some part of the chat message Flag (for example, the word or phrase). Words or phrases associated with translation failures include, for example, specialized / domain related terminology, abbreviations, acronyms, proper nouns, common nouns, reduced forms, colloquial words or phrases, and obscene words Or it may contain phrases. Further, a word or phrase may be flagged by a system or method that automatically detects that the word or phrase is untranslatable and possibly prevents translation of a larger phrase or sentence.

  The translation management module 1314 may be responsible for selecting a word or phrase as being subject to user feedback, where the selected word or phrase includes the actual translation of the text from the first language to the second language. Or it can be flagged as associated with a potential failure. The translation management module 1314 may select a word or phrase based on a number of factors. Some of these factors depend on the current importance of the word or phrase in the translation (eg importance based on the overall usage of the word or phrase) and the complexity of the word or phrase (eg the word or phrase Difficulty, or how long a word or phrase has been a problem), the suitability of the user who has chosen or volunteered to provide user feedback (eg, the user has a second language suitability), and provides user feedback And preferences of users who have chosen / volunteered to do. Those skilled in the art will appreciate that other factors for selecting words or phrases for user feedback may be utilized by various embodiments.

  For various embodiments, a user selected to provide user feedback may be a user who volunteers to provide such feedback. For example, by setting an associated user preference, by selecting in-chat system advertisements seeking user feedback, and / or a section listing one or more user feedback opportunities available for selection By browsing, the user may choose to provide user feedback.

  As shown herein, translation failure management 1314 manages when a particular word or phrase associated with an actual or potential translation failure is no longer a candidate for selection for user feedback by audience members. obtain. Depending on various conditions, translation failure management 1314 may determine when a particular number of feedback responses have been received, for example, in connection with a word or phrase, or in connection with an associated translation failure, Determining when a certain number of consistent feedback responses have been received in relation to a phrase or associated translation failure and a given feedback response as a valid response for the requested user feedback A determination may be made including determining when approved (eg, a particular response from a set of unique feedback responses was manually approved by the administrator as a correct response).

  The UF query generation module 1316 may be configured to generate a query for obtaining user feedback from a selected audience member for a given word or phrase selected for user feedback. As described herein, selected audience members may occasionally improve submitted user feedback when it is approved as correct, accepted as an accepted feedback response, or problem translation It may be a user who volunteered to provide user feedback in return for incentives when approved to be useful. More regarding the selection of audience members is described with respect to the UF query audience selection module 1318.

  For some embodiments, the generated query may include one or more methods for receiving a query response from the selected audience member. For example, the generated query is a predefined response (also referred to herein as a “select-form response”) that an audience member can select as a response to the generated query. A list may be included as a response method. In another example, the generated query may include one or more fields (referred to herein as “freeform responses” that are configured to receive text values entered into the fields by audience members in response to the generated query. (Also referred to as “free-form response”) as a response method. Other response methods may include graphical user interface (GUI) elements, text values, or some combination thereof.

  For example, the one or more response methods included in the generated query may be subject to many factors. Many such factors include, for example, audience member preferences, the importance and / or complexity of the word or phrase for which user feedback is sought, and the number of feedback responses received so far for the word or phrase for which user feedback is sought. And the number of consistent feedback responses received so far for the word or phrase for which user feedback is sought, and whether there are enough free-form feedback responses to create a selection form response. For some embodiments, the audience member who responds to the generated query may select from more than one response method for the generated query.

  Furthermore, the language in which audience feedback is provided to audience members may depend on many factors. The factors include, for example, whether the audience member is a multilingual speaker by monitoring the audience member's chat history, whether the audience member's language ability meets or exceeds a certain level of language certainty, Language settings on the user device that they are using to participate in user feedback opportunities (eg, default language settings for audience member devices). For example, if the default device language of an audience member's device is German and the audience member chooses to participate in user feedback opportunities, the query that is generated and sent to the audience member will be based on German. (For example, a query to define an English word or phrase to a German word or phrase, or vice versa). For some embodiments, the generated query may provide an audience member with an option to select the language of the response that will be submitted (eg, if the generated query does not specify or require a specific language). And / or may provide the audience member with an option to provide more than one response, where each response is possibly a different language. In some such embodiments, the audience member is subject to various language factors discussed herein, such as whether the audience member is a multilingual speaker and the language setting on the audience member's user device. Language response options can be provided.

  The UF query audience selection module 1318 may be configured to select audience members for user feedback. In some embodiments, the UF query audience selection module 1318 may optionally be from a pool of audience members who volunteered to provide user feedback in return for incentives (which may be received when user feedback is approved / accepted). Audience members can be selected. As described herein, an audience member may volunteer to participate in a translation, at which time the audience member selects an audience member that the UF query audience selection module 1318 selects for user feedback solicitation. Can be included in the pool. In some embodiments, when the UF query audience selection module 1318 selects an audience member, a query generated by the UF query generation module 1316 may be provided to the audience member to obtain user feedback. The query generated by the UF query generation module 1316 may be provided to the audience member selected by the UF query audience selection module 1318 as part of a list of user feedback available for participation by the selected audience member. Once the generated query is provided to the selected audience member, the selected audience member provides the generated query to the audience member (eg, by one or more response methods associated with the generated query). And a selected audience member may initiate a user feedback session that may provide one or more responses (eg, by one or more response methods included with the generated query).

  Depending on the embodiment, if a word or phrase is selected for user feedback before an audience member is selected, the selected word or phrase (e.g., the selected word or phrase is the aptitude or preference of the audience member). Audience members can be selected from a set of candidate audience members based on whether they match the reference. Alternatively, if an audience member is selected before a word or selection is selected for user feedback, the selected word or phrase may be based on the selected audience member. The suitability of a given audience member is determined by one or more feedback responses previously provided by that given audience member (eg, in connection with previous queries generated and provided to the given audience member). And / or may be determined based on one or more language skills of the audience member. An audience member, for example, may be evaluated as having the requisite qualities to provide user feedback for one or more words or phrases associated with a translation failure when achieving a certain number of approved feedback responses. In another example, an audience member is at least a feedback response previously submitted for a particular language, audience member preferences, and / or information related to the audience member that indicates the fluency of that particular language. Based on that, it can be evaluated as having aptitude in a particular language. In yet another example, an audience member who has submitted a feedback response (eg, a meaningless response or a forged response) that was previously evaluated as inaccurate or fraudulent may be determined to have low suitability.

  In some embodiments, once a given audience member provides a response with respect to a word or phrase (and the response is optionally approved), the given audience member may be the user for the same word or phrase. It may not be reselected to provide feedback. Some embodiments may make an exception to this restriction if a given audience member provides responses in a language different from the language of responses previously submitted for the same word or phrase.

  When incentives are provided in return for user feedback (eg, upon approval of a feedback response), various embodiments provide time-based quotas (eg, hourly, daily, monthly for submitting feedback responses) Audience members may be selected based on quotas such as in-game currency or item limits granted for incentive-based user feedback. The allocation is associated with an individual audience member, a group of audience members, or some combination thereof. For some embodiments, the UF query audience selection module 1318 may use computing resource availability for user feedback, incentives given in connection with user feedback, quality of feedback responses received in the past, etc. The availability of user feedback opportunities to one or more audience members may be suppressed or stopped based on various conditions such as:

  A query / response (QR) pricing module 1320 is configured to determine the value or importance of a query or query response based on the word or phrase for which the query or query response is seeking user feedback. obtain. Examples of factors that may be considered by various embodiments in determining the value of a query or query response include word or phrase complexity (eg, the higher the complexity, the higher the value), the word for the translation / translation process, or The importance of the phrase (eg, the higher the importance, the higher the value), the response method used by the query or inquiry response (eg, the higher value for the freeform response method than the selection form response method), word or phrase A type of (e.g. chat term, abbreviation, or colloquial) or one or more included languages (e.g., a query containing an English word or phrase that receives a French response receives an English response, Have a higher value than queries that contain English words or phrases). In some embodiments, the incentive provided for a given user feedback may be based on a value associated with the query or query response. For some embodiments, the QR pricing module 1320 determines values for a query or query response based on the validity of a previous query or query response when seeking useful, useful, or accurate user feedback. Can be configured to. Thus, for some embodiments, the value can be dynamically adjusted based on the latest validity of what was achieved by the previous query or query response. In some embodiments, the QR pricing module 1320 can be manually configured by an administrator (eg, of the CTT system 1300) or another authorized user in connection with one or more user feedback for queries and / or query responses. It may be possible to assign or adjust.

  Query API module 1322 may be configured to facilitate sending user feedback queries to selected audience members and / or receiving query responses from selected audience members. In some embodiments, the query API 1322 provides a list of user feedback opportunities available to the selected audience member and provides a query regarding one or more user feedback opportunities selected by the selected audience member. Receive a response for one or more user feedback opportunities selected by the selected audience member and / or the current status of the query response so far submitted for approval (eg, approved, rejected, or (Pending approval / status pending approval) may be adapted to be provided to selected audience members. For some embodiments, the query API 1322 may be associated with a given audience member from a chat client system, possibly used by the given audience member, to interact with the CTT system 1300. Can be obtained. As shown herein, a preference associated with an audience member may determine a word or phrase selection for which user feedback is sought from the audience member and / or for user feedback for a given word or phrase It may be determined whether an audience member is selected to receive the query.

  Response evaluation module 1324 may be configured to evaluate a query response submitted in connection with a query generated to obtain user feedback. For some embodiments, the response evaluation module 1324 may evaluate the query response in one or more phases.

  During the validation phase, the response evaluation module 1324 treats one or more unique responses submitted for a given generated query as approved or rejected for the given generated query. obtain. In some embodiments, a unique response submitted in connection with a query generated to obtain user feedback acknowledges that the unique response is valid for the word or phrase associated with the generated query. Can be considered pending until the time it is done or until it is rejected as invalid for the word or phrase associated with the generated query. As used herein, a given “unique response” may include a set of responses that are similar in syntax but not necessarily identical (eg, different punctuation or spacing). A given unique response may be received by more than one response method. The unique response is also referred to herein as “unique query response” and “unique user feedback response”. Depending on the embodiment, more than one unique query response may be approved for a given generated query. For example, more than one unique response may be approved as defining a given word or phrase for the user feedback sought. The response can be manually enabled, for example, by an administrator who reviews and treats the response (eg, only unique responses in some cases). Additionally or alternatively, responses can be validated by an automated process that can approve and / or reject submitted responses based on their counts and / or thresholds associated with response counts. In some embodiments, the auto-validation process may filter the top submitted responses for a given word or phrase and provide those top submitted responses to an administrator etc. for review and treatment Can do. The validation phase may be based on a response evaluation module 1324 on a periodic basis (eg, based on a schedule) or on a condition (eg, when the number of submitted responses pending approval meets or exceeds a threshold). Can be executed by

  In some embodiments, if multiple unique user feedback responses (eg, definitions) are provided for a given word or phrase, response evaluation module 1324 can automatically (and / or manually admin input). Can approve a top-rank unique user feedback response (eg, the most common response) of the plurality of unique user feedback responses, but the top-rank unique user feedback response is statistically significant. This can only be done if For example, if a first unique user feedback response is received 26 times for a given word and a second unique user feedback response is received 24 times for the same given word, the first unique user feedback response A user feedback response cannot be approved as a response for a given word, even if it is a top-rank unique user feedback response for a given word. This is because 26 times is not statistically significant compared to 24 times. For example, the first unique user feedback cannot be selected until the first unique user feedback response remains the top rank unique user feedback response and the response count reaches 40.

  Given that phrases are not identical but are similar in nature and can convey the same intent, in some embodiments, a word error rate (WER) is used to group unique user feedback responses containing phrases. error rate) can be used. For two phrases, WER may measure word substitution, deletion and insertion to convey similarities between phrases.

  In various embodiments, if multiple unique user feedback responses (eg, definitions) are provided for a given phrase, the response evaluation module 1324 may automatically (and / or through manual admin input) Can approve unique user feedback responses.

  During the check phase, the response evaluation module 1324 may determine whether the response submitted by the audience member has been treated as being approved, rejected, or pending verification (eg, pending approval). In some embodiments, the data store determines whether a unique response submitted by an audience member associated with a given word or phrase has been accepted or rejected as a valid definition for the given word or phrase. Can maintain status. Thus, the check phase determines the response action submitted for a given word or phrase by querying a data store that maintains the action status of the unique response previously submitted for the given word or phrase. The submitted response may share a unique response action status corresponding to the submitted response. Depending on the embodiment, the check phase for submitted responses may be performed immediately or immediately after the response is submitted. If it is determined that the submitted response is still pending validation during the check phase, the check phase may be re-executed later, and possibly after the validation phase, so that it is the same or similar The status of the submitted response will be affected. The status of the submitted response may be updated according to the current action of the submitted response as determined during the check phase. As described herein, the current status of one or more responses submitted by a given audience member may be provided as a list reflecting the current status for those responses. More about response status is discussed below in connection with FIG.

  Response evaluation of response evaluation module 1324 may include determining whether the response is approved. The response may be approved based on at least one previous response provided by another person in response to another query previously generated to obtain feedback on the word or phrase from the other person. Once it is determined that the response accurately defines a word or phrase, the response can be approved.

  The translation data store update module 1326 is configured to update a translation or translation (eg, stored in the conversion data store 210), possibly based on an evaluation of a response submitted for a user feedback query by a selected audience member. Can be configured. For example, if during a response evaluation it is determined that the submitted response in the first language is an approved definition for a given word in the (same) first language, the first A transformation that maps a given word in a language to a response in a first language may be added or updated. In another example, during a response evaluation, if it is determined that the submitted response in the second language is an approved definition for a given word in the first language, the first A transformation that maps a given word in one language to a second language response may be added or updated. Translation or translation updates may be performed by the translation data store update module 1326 during or after the check phase, and actions are taken to make the submitted response approved.

  Audience suitability assessment module 1328 may be configured to determine audience member suitability that may indicate a level of certainty associated with the audience member's ability to provide an accurate and / or useful user feedback response. As described herein, the suitability of a given audience member has been previously provided by the given audience member (eg, in connection with a previous query that was generated and provided to the given audience member). Can be determined based on the one or more feedback responses made and / or one or more language abilities of the audience member. For example, an audience member may be evaluated as having the requisite qualities to provide user feedback for one or more words or phrases associated with a translation failure when achieving a certain number of approved feedback responses. In another example, an audience member is at least a feedback response previously submitted for a particular language, audience member preferences, and / or information related to the audience member that indicates the fluency of that particular language. Based on that, it can be evaluated as having aptitude in a particular language. In yet another example, an audience member who has previously submitted a feedback response (e.g., an unintelligible response) that was previously evaluated as inaccurate or fraudulent may be determined to have low suitability.

  The incentive reward module 1330 may be configured to provide incentives to audience members based on the evaluation of responses submitted by audience members in connection with queries for user feedback. As described herein, incentives may be given to audience members upon approval of a submitted response. The amount or type of incentive provided can be determined based on a number of factors. Many such factors include the value of the query or query response assigned by QR pricing module 1320, the response method used by the audience member in responding to the query, (eg, in connection with a particular word or phrase or The amount of incentives already given to audience members or all audience members through incentive-based user feedback, the language of the query or response provided, and the type of word or phrase for which the response was submitted (for example, chat terms) , Abbreviations or special domain words or phrases). The incentives given may be real world currency or in-game currency that may or may not have value outside its associated virtual economy (eg, monetary value in the real world economy) Or it may include virtual currency such as in-game items. In some embodiments, incentives may include real world goods or services, or virtual goods or services that may have an associated monetary value. Those skilled in the art will recognize that other forms of incentives may be provided in different embodiments.

  In some embodiments, the incentive reward module 1330 may be used if one or more of the submitted responses are approved and / or if an incentive is given to the audience member for the approved submitted response. , Can be responsible for notifying audience members. In various embodiments, incentive reward module 1330 may notify audience members of incentive rewards through notification messages (eg, in-chat messages such as pop-up messages) and / or updates to a list of status for submitted responses. .

  One skilled in the art will recognize that for various embodiments, the system for user feedback may include more or fewer components than those shown in FIG. 13, and each component shown in FIG. 13 is described for each component. It will be appreciated that more or fewer operations may be performed.

  FIG. 14 is a block diagram illustrating an exemplary user feedback client system in accordance with various embodiments. For exemplary purposes, in FIG. 14, a user feedback client system is shown as part of a chat client system 1400 according to various embodiments. For example, a typical user feedback client system may be part of a game chat client system (eg, an in-game chat client system) that is available in connection with an MMO game. Various players in an MMO game may choose to provide user feedback for a flagged word or phrase, possibly in return for in-game currency / credit / items as an incentive for feedback. Those skilled in the art will recognize that for some embodiments, typical system user feedback, some or all of its associated components may be separate from the typical communications conversion and translation system 1300. Will.

  As shown in FIG. 14, chat client system 1400 may include a chat client controller 1402, a chat client communication module 1404, and a chat client graphical user interface (GUI) module 1406. In some embodiments, chat client controller 1402, chat client communication module 1404 and chat client GUI module 1406 are similar to components of chat client system 104, as described herein.

  As further shown in FIG. 14, chat client system 1400 includes a transformation / user feedback (UF) query preference module 1408 and a transformation / user feedback (UF) query graphical user interface (GUI) module 1410. For some embodiments, the UF query preference module 1408 and / or the UF query GUI module 1410 facilitate user feedback interaction with the CTT system 1300. In the context of chat client system 1400, a chat user of chat client system 1400 may be an audience member for various embodiments of a user feedback system (eg, CTT system 1300).

  The UF query preference module 1408 may preview, define, and / or adjust preferences with respect to user feedback functionality provided in connection with a user feedback system (eg, CTT system 1300) of some embodiments. It can be configured to manage and otherwise allow chat users. Examples of preferences managed by the UF query preference module 1408 include, for example, language preferences for user feedback (eg, the language of the word or phrase for which user feedback is sought and / or the language of the user feedback sought), user feedback query Preferred response methods (eg, select form responses to free form responses), or preferred word or phrase types (eg, abbreviations, chat terms, physics related, or idiom), etc.

  As used herein, a select form response is a response that is predetermined and can be selected from a list of two or more select form responses. Depending on the embodiment, the list of select form responses may allow audience members to select more than one response, if applicable. A free-form response is a response (eg, a character value or a string value) that includes a text-based value entered into a field by an audience member.

  The UF query GUI module 1410 is presented for user feedback (eg, by the CTT system 1300) and presented to the chat user, presents one or more response methods associated with the query, and / or is presented. Receiving a response from a chat user through a different response method can be facilitated graphically. The UF query GUI module 1410 may further facilitate management of preferences through a UF query preference module 1408. More about the graphical user interface that can be presented in the chat client system is described below with respect to FIGS. 17-23 and 24-31.

  Those skilled in the art will appreciate that in various embodiments, a client system for user feedback may include more or fewer components than those shown in FIG. 14, and each component shown in FIG. 14 is described for each component. It will be appreciated that more or fewer operations may be performed than performed.

  FIG. 15 is a flowchart illustrating an exemplary method 1500 for user feedback in accordance with various embodiments. In step 1502, the translation failure management module 1314 may optionally identify a potential failure in converting or translating text from the first language to the second language. In step 1504, translation failure management module 1314 may further select a word or phrase from the identified potential failures for user feedback. At step 1506, the UF query audience selection module 1318 may select audience members for soliciting user feedback. In step 1508, the UF query generation module 1316 may generate a query to obtain user feedback from possibly selected audience members. In step 1510, response evaluation module 1324 may receive a response to the generated query. The query API module 1322 may be responsible for providing the generated query to the selected audience member and receiving a response to the generated query. In step 1512, response evaluation module 1324 may evaluate the received response. At step 1514, audience suitability assessment module 1328 assesses the suitability of the selected audience member, possibly based on the response provided at step 1510 and / or the assessment of the response received when executed at step 1512. Can do. At step 1516, the incentive reward module 1330 may incentivize the selected audience member based on the response evaluation. As shown herein, in evaluating the response and determining that it is approved, the incentive reward module 1330 may respond to a query response as determined by the query value and / or QR pricing module 1320. Therefore, rewards can be given to audience members. At step 1518, translation data store update module 1326 may update the translation or translation based on the response evaluation. As shown herein, once the response is evaluated and determined to be approved, the translation data store update module 1326 updates the translation or translation corresponding to the query and the submitted query response word or phrase. obtain.

  FIG. 16 is a block diagram illustrating an exemplary data flow 1600 for a user feedback system in accordance with various embodiments. As shown, data flow 1600 includes chat client system 1400, translation failure management module 1314, UF query generation module 1316, UF query audience selection module 1318, response evaluation module 1324, translation data store update module 1326, and incentive reward module. 1330 is included. Data flow 1600 further includes an undefined word / phrase data store 1602, a recorded response data store 1604, a feedback audience data store 1606, a response approval data store 1608, a chat data store 1610, and a dictionary data store 1612.

  The undefined word / phrase data store 1602 may include words or phrases that are associated with translation failures and that require user feedback. The undefined word / phrase data store 1602 includes a word or phrase, a sample sentence in which the word or phrase is used (eg, the context of the word or phrase), and a certainty measure that indicates how important the word or phrase is (eg, Word importance), the source language for the word or phrase, the target language for the required user feedback, etc. In some embodiments, the significance of a word or phrase word in the undefined word / phrase data store 1602 may initially be equal for all words, but the word or phrase appears to be a problem and / or Or increase if you can't translate.

  The recorded response data store 1604 may include user feedback responses received from audience members and recorded for words or phrases included in the undefined word / phrase data store 1602. In some embodiments, the user feedback response includes a response received for a query generated to obtain user feedback for a word or phrase. The undefined word / phrase data store 1602 includes a recorded user feedback response, an identifier for the audience member submitting the user feedback response, and a time stamp for when the user feedback response was received and / or recorded. , Indicating whether the recorded user feedback response is approved, a time stamp for when the recorded user feedback response was approved, and the like.

  The feedback audience data store 1606 may include a set of identifiers for audience members that are selected to participate in user feedback for words or phrases included in the undefined word / phrase data store 1602. The feedback audience data store 1606 may include each identifier for the audience member and a certainty score that reflects the consistency, suitability and / or certainty of the audience member in providing the user feedback response.

  Response approval data store 1608 may include each unique user feedback response received in association with a word or phrase included in undefined word / phrase data store 1602. The response approval data store 1608 includes each unique user feedback response and a unique user feedback response that is an approved response (eg, a correct response), a rejected response (eg, an incorrect response), a review pending response ( For example, a response that needs to be considered) or an indication of whether the response has some other status. In some embodiments, the response approval data store 1608 may be used in determining when a user feedback response received from an audience member and recorded in the recorded response data store 1604 has been approved.

  According to some embodiments, the translation failure management module 1314 reviews the chat log, possibly provided by the chat data store 1610, and one or more words or associated with actual or potential translation failures. It may be configured to identify a phrase. In various embodiments, the translation failure management module 1314 may use a standard dictionary (eg, an Oxford dictionary) and / or words or phrases (eg, that the embodiments described herein can parse, recognize, and / or handle). Chat terms words or phrases) may be configured to exclude those words or phrases defined in the dictionary data store 1612 that may include a dictionary. Words or phrases identified by the translation failure management module 1314 can be added to the undefined word / phrase data store 1602 such that the added words and phrases are for user feedback from the selected audience member. Allows to be selected.

  The translation failure management module 1314 may be configured to select one or more words or phrases from the undefined word / phrase data store 1602 in some cases for user feedback. For some embodiments, translation failure management module 1314 may select from a set of words or phrases designated as having the highest importance in undefined word / phrase data store 1602 (eg, undefined word / phrase Selected from the top 10 important words or phrases in the phrase data store 1602). In some embodiments, the translation failure management module 1314 should choose to respond (eg, allow the audience member to choose the user feedback that they feel most confident to respond to) more than one user feedback. More than one word or phrase may be selected so that a set of can be provided to an audience member. The selection process by the translation failure management module 1314 from the undefined word / phrase data store 1602 includes the importance of the word or phrase, the timing of the word or phrase in the undefined word / phrase data store 1602, and the UF query audience selection module 1318. The preference of the selected audience member by and whether the audience member selected by the UF query audience selection module 1318 has already responded to the selected word or phrase (eg, recorded for the selected word or phrase) Based on checking the response data store 1604) and the like.

  The UF query audience selection module 1318 may be configured to optionally select one or more audience members from the feedback audience data store 1606 for which user feedback may be sought. As described herein, user feedback may be sought for words or phrases that are optionally selected from the chat data store 1610 by the translation failure management module 1314. The selection of audience members from the feedback audience data store 1606 may depend on the suitability level associated with the audience member.

  The UF query generation module 1316 is configured to generate one or more queries for words or phrases selected by the translation failure management module 1314, possibly from the undefined word / phrase data store 1602, for user feedback. obtain. As shown, translation failure management module 1314 may provide UF query generation module 1316 with selected words or phrases for which one or more queries are generated. As described herein, the UF query generation module 1316 may include, for example, audience member preferences selected by the UF query audience selection module 1318 and words or phrases selected for user feedback by the translation failure management module 1314. Many different factors may be considered when generating a query that includes As a result, the UF query generation module 1316 may provide one or more queries generated by the UF query generation module 1316 to the chat client system 1400, with different queries for each word selected and provided by the translation failure management module 1314. Could be produced.

  As a result, one or more queries generated by the UF query generation module 1316 can be provided to the chat client system 1400, thereby presenting the provided queries for selection by the user at the chat client system 1400. To do. Depending on the embodiment, the UF query generation module 1316 may provide the generated query to the chat client system or alternatively provide another generated query to the chat client system. A component can carry. Once the generated query is presented for selection at the client chat system 1400, the user of the client chat system 1400 may select to respond to one or more of the presented queries, and the chat client system Those responses provided by 1400 may be added (eg, recorded) to the recorded response data store 1604.

  When a response is added to the recorded response data store 1604, some embodiments check that the added response can be evaluated by the response evaluation module 1324. As described herein, the response evaluation module 1324 may evaluate responses by checking and treating responses and response status.

  As shown in FIG. 16, the response evaluation module 1324 includes a response check module 1614 that is configured to perform a status check of the user feedback response during the evaluation of the user feedback response. Can be done. The response check module 1614 extracts the user feedback response from the recorded response data store 1604 and checks the status of the unique response in the response approval data store 1608 corresponding to the extracted user feedback response to The status of the user feedback response from chat system 1400 may be checked. In doing so, the response check module 1614 may determine whether a given user feedback response is accepted or rejected. The approval status of the extracted user feedback response in the recorded response data store 1604 may be updated according to the latest status check performed by the response check module 1614. If the response check module 1614 determines that the extracted user feedback response is approved, the approval status of the extracted user feedback response in the recorded response data store 1604 reflects the approval and the approval status is updated. May be updated to include a time stamp for when it was made. As a result, with the approval reflected in the recorded response data store 1604 for the extracted user feedback response, the incentive reward module 1330 may incentivize the audience member who submitted the approved user feedback response.

  If the status of the extracted translation response is still pending review, the response check module 1614 may recheck the status of the extracted user feedback response later (eg, according to a predetermined schedule). If the status of the extracted translation response is rejection, the approval status of the extracted user feedback response in the recorded response data store 1604 can be updated to reflect the rejection.

  If a unique response corresponding to the extracted user feedback response is not found, the extracted user feedback response is a unique for the word or phrase for which the user feedback response was provided (eg, by a user of chat client system 1400). It can be added to the response approval data store 1608 as a response. Further, if the extracted user feedback response is added to the response approval data store 1608 as a unique response, the unique response may have an initial status pending approval, where the initial status pending approval is a unique response. It remains until the response status is handled manually or automatically (eg, through the evaluation response module 1324).

  As shown in FIG. 16, the response evaluation module 1324 further includes a response validator 1616, which displays the status of the unique user feedback response as approved, rejected, or pending approval. May be configured to treat. As described herein, a unique user feedback response submitted in connection with a query generated to obtain user feedback is a word or word associated with the generated query or unique user feedback response. It may be considered pending approval until it is approved as valid for a phrase or rejected as invalid for a word or phrase associated with the generated query.

  For some embodiments, the response evaluation module 1324 may be configured to determine if a given word or phrase no longer requires further user feedback. The response evaluation module 1324 determines how many unique user feedback responses are approved for a given word or phrase and the count of unique and approved user feedback responses meets or exceeds a certain threshold. Such a determination may be made based on an example of a factor such as whether or not. If it is determined that a given word or phrase no longer requires further user feedback, response evaluation module 1324 may be configured to remove the given word or phrase from undefined word / phrase data store 1602. This removes words or phrases from future selections for user feedback (eg, by translation failure management module 1314).

  As described herein, once the provided user feedback response is approved as a valid response for the word or phrase for which the user feedback response was provided (eg, by an audience member through chat client system 1400) The incentive reward module 1330 may provide incentives to the audience member. The incentive reward module 1330 has recently been approved in the recorded response data store 1604 (eg, the approval status has been recently updated to reflect the approval) and / or the recorded response has a status that the incentive reward module 1330 has been approved. One or more user feedback responses that have been approved since the last attempt to identify one or more user feedback responses in the data store 1604 may be identified. The incentive reward module 1330 may determine when a given user feedback response was last approved based on an approval timestamp included in the recorded response data store 1604 for the user feedback response. For some embodiments, once an incentive is given for a translated feedback response in the recorded response data store 1604, the translated feedback response may be removed from the recorded response data store 1604. Alternatively, once an incentive is provided for the translated feedback response in the recorded response data store 1604, the translated feedback response may be, for example, when the incentive was given, or the amount of incentive given Updated in the recorded response data store 1604 to indicate the type of incentive given, when the audience member was notified about this reward, and / or how the audience member was notified about the given incentive Can be done.

  FIG. 17 illustrates an exemplary screenshot for receiving user feedback for a word in accordance with various embodiments. In particular, FIG. 17 shows screenshots 1702, 1704, and 1706 that represent examples of GUIs that may be presented to audience members (eg, through chat client system 1400) to facilitate the user feedback process. Screenshot 1702 provides an example of a banner 1708 that asks one or more audience members to participate in user feedback for a word or phrase associated with a translation failure. An audience member may choose to participate in user feedback by selecting a banner 1708, which may lead to the start of a user feedback session and / or may choose to participate in the audience member. Lead audience members to a list of available user feedback opportunities. As described herein, user feedback opportunities may allow audience members to provide definitions for words or phrases associated with actual or potential translation failures. According to some embodiments, the audience member may select one of the available user feedback opportunities associated with the word or phrase, and then, when prompted, provide a definition for the associated word or phrase. obtain.

  Screenshot 1704 presents a list 1710 of available user feedback opportunities for various words (eg, “Skrilla”, “Booty”, “Cray”, “Hecka”, and “Freshness”). Screenshot 1706 provides an example of a query 1712 presented to an audience member to obtain user feedback for the word “Skrilla”. As shown, query 1712 provides an exemplary context 1714 in which the word “Skrilla” is used, and further provides a field 1716 that is configured to receive a free-form response for query 1712. Once the audience member selects user feedback for the word “Skrilla” from the list 1710 in the screenshot 1704, the audience member may be directed to the screenshot 1706.

  FIG. 18 illustrates an exemplary screenshot for skipping user feedback in accordance with various embodiments. In particular, FIG. 18 shows screenshots 1802 and 1804 representing examples of GUIs that can be presented to audience members (eg, through chat client system 1400) to facilitate the user feedback process. Screenshot 1802 presents a list 1806 of user feedback opportunities available for selection by audience members. As shown, list 1806 provides audience members with an option to skip one or more of the user feedback opportunities on the list.

  Screenshot 1804 presents an example of a query 1808 that is presented to audience members to obtain user feedback for various words. As shown, query 1808 provides the audience member with an option to skip the process of providing a response to query 1808. Certain embodiments avoid inaccurate and / or forged responses to various user feedback queries by providing audience members with an option to skip certain user feedback opportunities and / or various user feedback queries. obtain.

  FIG. 19 illustrates an exemplary screenshot for receiving user feedback for a phrase in accordance with various embodiments. In particular, FIG. 19 shows screenshots 1902 and 1904 representing examples of GUIs that may be presented to audience members (eg, through chat client system 1400) to facilitate the user feedback process. Screenshot 1902 presents a list 1906 of user feedback opportunities available for selection by audience members. As shown, there is a list 1906 of user feedback opportunities available for various words and phrases (eg, “Skrilla” and “Pardon my french”).

  Screenshot 1904 provides an example of a query 1908 presented to an audience member to obtain user feedback for the phrase “Pardon my french”. As shown, query 1908 provides an exemplary context 1910 in which the phrase “Pardon my french” is used, and further provides a field 1912 that is configured to receive a free-form response for query 1910. Once the audience member selects user feedback for the phrase “Pardon my french” from the list 1906 in the screenshot 1902, the audience member may be directed to the screenshot 1904.

  FIG. 20 illustrates an exemplary screenshot for receiving user feedback through a list of select form responses according to various embodiments. In particular, FIG. 20 shows screenshots 2002, 2004, and 2006 that represent examples of GUIs that can be presented to audience members (eg, through chat client system 1400) to facilitate the user feedback process. Screenshot 2002 presents an example of a banner 2008 that prompts one or more audience members to participate in user feedback for a word or phrase associated with a translation failure. An audience member may choose to participate in user feedback by selecting a banner 2008, which may lead to the start of a user feedback session and / or may choose to participate in the audience member. Lead audience members to a list of available user feedback opportunities.

  Screenshot 2004 provides an example of a query 2010 presented to an audience member to obtain user feedback for the word “Skrilla”. The inquiry 2010 includes a select form response 2012, and the select form response 2012 lists responses that can be selected by the audience member. Screenshot 2006 presents an incentive (eg, 5 gold coins) given by notifications 2014 and 2016 once the correct response “money” is selected for the word “Skrilla”.

  FIG. 21 illustrates an exemplary screenshot for creating a list of choices according to various embodiments. In FIG. 21, screenshot 2102 provides an example of a query 2106 presented to audience members to obtain user feedback for the word “Skrilla”. As shown, query 2106 provides an exemplary context 2108 where the word “Skrilla” is used, and further provides a field 2110 that is configured to receive a free-form response for query 2106.

  According to some embodiments, the select form response method used to obtain user feedback for a given word or phrase is pre-defined from a free form response collected for the given word or phrase. May contain a list of received responses. Thus, when various audience members provide free-form responses (eg, “A lot of money”, “Cash”, “Money”, and “Really Rich”) through the field 2110 for the word “Skrilla”, screenshot 2104 shows As collected, the collected responses may be useful in creating a list of selected form responses 2112.

  FIG. 22 shows a screenshot illustrating an exemplary incentive notification in accordance with various embodiments. In FIG. 22, screenshot 2200 notifies an audience member of the approval of the “money” response for the word “Skrilla” and the incentive given to the approved response (eg, XXXG Gold). An example of notification is presented. Screenshot 2202 presents an example of a notification to an audience member, notifying the rejection of the “money” response for the word “Skrilla”. Screenshot 2204 presents an example of a push notification to an audience member that notifies the approval of the response.

  FIG. 23 shows a screenshot illustrating an example when translation fails between client chat systems, according to various embodiments. In FIG. 23, screen shot 2300 represents a typical interface of the first chat client system, and screen shot 2302 represents a typical interface of the second chat client system. A double arrow 2304 represents chat communication between the first chat client system and the second chat client system. As shown, when chat user “Aramis” inputs chat communication in English into the interface of the first chat client system, the input chat communication is translated into French and the second chat of chat user “tapir”. Presented on the client system interface. Similarly, when the chat user “tapir” inputs chat communication in French to the interface of the second chat client system, the input chat communication is translated into English and the first chat client system of the chat user “Aramis”. Presented on the interface.

  As shown in FIG. 23, the chat communication 2306 (that is, “Tru dat bro”) input to the interface of the first chat client system by the chat user “Aramis” is the second chat client of the chat user “tapir”. Translation fails when sent to the system interface. Chat communication 2308 presented to chat user “tapir” (ie “Tru dat bro?”) Presents the original chat communication entered by chat user “Aramis”, and this chat communication is the chat user “Aramis”. "Tapir" indicates to the chat user that it is the original chat message input by "" to reflect this translation failure.

  The translation failure illustrated by FIG. 23 may be one that can benefit from user feedback according to some embodiments. According to some embodiments, the translation failure shown in FIG. 23 may be identified by the translation failure management module 1314, where one or more words from the original chat communication 2306 (ie, “Tru dat bro?”) User feedback from participating audience members may be added to the undefined word / phrase data store 1602 for future selection. For example, each word “Tru”, “dat”, and “bro” may be added to the undefined word / phrase data store 1602 for each future user feedback.

  FIGS. 24 and 25 show screenshots illustrating an exemplary list of words or phrases available for user feedback in accordance with various embodiments. In FIG. 24, screenshot 2400 presents a list 2402 of user feedback opportunities available for audience member selection for words and phrases (including “Tru”) that are available for selection by audience members. In FIG. 25, screenshot 2500 presents another list 2502 of user feedback opportunities available for audience member selection for phrases available for selection by audience members. In both FIG. 24 and FIG. 25, screenshots 2400 and 2500 can be part of an in-game chat system so that the game player can provide user feedback for a word or phrase and upon approval of the feedback response. In-game credits (eg, in-game gold) may be awarded.

  FIG. 26 shows a screenshot illustrating an example of defining a word according to various embodiments. In FIG. 26, screenshot 2600 shows a query 2602 that includes an exemplary context 2604 where the word “Tru” is used, and further provides a field 2606 that is configured to receive a free-form response to query 2602. .

  FIG. 27 shows a screenshot showing an exemplary list of select form responses according to various embodiments. In FIG. 27, screenshot 2700 presents a list 2702 of responses that an audience member can select to define the word “nemore”.

  FIG. 28 illustrates a screenshot showing an exemplary list of status for responses submitted in accordance with various embodiments. As shown in FIG. 28, the submitted response status list 2802 includes pending status for the first response 2804 and approval status for the second and third responses 2806 and 2808. For some embodiments, the list 2802 may provide further information about response status including, for example, why a particular response is approved, rejected, or still pending review.

  FIG. 29 shows a screenshot showing a typical incentive notification, according to various embodiments. In particular, FIG. 29 shows a screen that presents a typical notification 2902 to the member to accurately define the phrase “U still thr” as “You still there?” During the user feedback process according to the embodiment. A shot 2900 is provided. The notification indicates that the user will be given ten gold pieces that may be valuable or useful as in-game currency as an incentive for user feedback provided. As shown, the notification further provides a summary of user feedback (ie, the word or phrase in question and the provided user feedback response).

  In one embodiment, a learning system for data selection is provided in which feedback obtained from a user is automated by a machine learning system that has check and balance for player consistency. The system adds parallel sentences received from the player to a parallel corpora that can be used to retrain the statistical machine translation (SMT) system from time to time.

  The chat conversion system can be or can include a system that converts chat terms into plain speak. For example, chat conversion may convert “U r da king” (chat term message) to “You are the king” (plain message). In one embodiment, “plain language” refers to a normal language normally spoken and / or described by a normal individual outside an electronic chat environment where chat terms may dominate. Plain language tends to be more grammatical than chat terms.

  The learning system may further utilize or include a language translation system that translates one language into another language. For example, for language translation, “How are you doing kind sir” (English message)

"(Spanish message).
In some embodiments, a “translational corpus” is two texts, one text for each language arranged in parallel so that line n in one text corresponds to line n in the second translated text. Understood to mean text. A bilingual corpus is also referred to as a “training corpus” in such a context.

  In various embodiments, “machine learning” refers to a supervised, semi-supervised, or unsupervised system that can learn from patterns in input data and develop mechanisms to detect, transform, or predict behavior. It is understood.

  In general, the construction of a chat conversion system and a language translation system requires an appropriate amount of syntax rules or a large number of parallel corpora for statistical learning. The systems and methods generally described herein utilize a reliable statistical chat conversion and language translation system that uses a bilingual corpus. However, in some circumstances, this initial training data set may be limited in its content and scope. For example, new chat words are created daily and added to the chat room. In order to maintain an accurate and reliable conversion and translation system, these new chat words should be supplemented to the chat conversion training corpus.

  In various embodiments, systems and methods are provided for identifying words that are “Out of Vocabulary” (eg, words that do not exist in a given vocabulary). In some embodiments, referring to FIG. 30, a method 3000 is provided for detecting and processing OOV words. In step 3002, an OVV word is first detected by transmitting the OVV word through a translator system, such as CTT system 114 or CTT system 1300 and / or one or more modules thereof. If the output from the translator system is the same as the input for a given word, the translator system indicates a lack of translatability that suggests that the word may be an OOV. To further evaluate a word as a potential OOV word, the system and method may determine whether the word is a new word rather than just a misspelled word (step 3004). Both misspelled words and new words will appear as OOVs. Thus, a word that can be corrected with a spell checker can be considered a misspelled word rather than an OOV word.

  Furthermore, OOV words that frequently appear in chat are generally more likely to be OOV words (eg, new chat talk words). For example, if a word has been used by a user in a previous text message, such previous use suggests that the word may be an OOV word. In some embodiments, an ensemble of machine learning and language processing methods is used in parallel to detect whether the word is an OOV word (step 3006).

  Additionally or alternatively, a Bayesian probability may be calculated to provide a statistical probability when the OOV is a new word rather than a misspelled word (step 3008). Pure chat terms generally tend to follow certain words that are used before or after the chat term. In comparison, spelling errors have a less consistent distribution for adjacent words. Calculating prior and posterior Bayesian probabilities helps to distinguish useful OOV words that can be added to the vocabulary from spelling errors that should not be added to the vocabulary. The For example, consider the phrase “Wassup, how's it going”. Since “Wassup” does not exist in the standard vocabulary, it is considered an OOV word. However, "Wassup" is almost always followed by the word "How's it going" or "Wassup" is often used at the beginning of a sentence. This pattern or consistent behavior is captured by Bayesian probabilities. The system is trained with text that has misspelled words but no chat words.

  Alternatively or additionally, machine learning methods such as k-means clustering may be used to distinguish different types of OOV words such as new chat words, misspelled words or junk (step 3010). . k-means clustering tends to provide hidden similarity between word classes. Words belonging to similar topics tend to be clustered together, thereby indicating hidden similar semantic relationships between them. Again, consider the example of “Wassup, how's it going”. By clustering groups of sentences using the k-means algorithm, in a cluster of greeting words such as "Hi", "What's up", "Hello", "Hi!" It becomes clear that is included. In contrast, spelling errors will be located at the edge of the cluster or not at all in any defined cluster. These hidden relationships help distinguish useful OOV words from errors. The syntax and meaning of the sentence can be analyzed to determine what kind of OOV word (eg, verb, noun or adjective) the sentence contains.

  When the system and method detect a new chat word or other OOV word, the new chat word is presented to a human translator to define a translated or language translated version of the chat. . Thereafter, translated or translated versions of new chat words can be added to the translated vocabulary and used by the systems and methods described herein.

  As described herein, if an incentive is provided for manual translation of chat between languages, the user may operate the system illegally to misuse the incentive (eg, in-game currency). is there. The systems and methods described herein can detect fraudulent submissions, but are generally tolerant of human translator capabilities.

  When a system user acts as a translator, the user translates one or more words or sentences into a specified target language. However, if the user gives incorrect, incomplete or inappropriate translations in order to deceive the system or to gain incentives without meeting the purpose of the system, the user commits cheating Yes.

  In some embodiments, referring to FIG. 31A, the systems and methods described herein utilize a fraud detection module 3100. The cheating detection module 3100 detects cheating in an incentive translation by presenting both new training data and old training data (eg, a bilingual corpus) to the user. Old training data corresponds to translations where the correct answer is known, while new training data corresponds to translations where the correct answer is unknown. The percentage of new data relative to old data can vary for the user over time. For example, initially older data may be shown and then the percentage may be gradually reduced.

  In some embodiments, fraud detection is performed by checking the accuracy of the translation of old data received from the user. Based on this accuracy, a certainty score is assigned to each user. A large or sudden change in translation accuracy, or consistently low accuracy, indicates fraud or poor translation ability in the user. Even after establishing the certainty of the translator's ability, the old data is preferably randomly embedded at least 10-20% of the time for periodic fraud checks.

  Using this basic structure, cheating detection module 3100 may include and / or utilize supervised cheating detection module 3102 and / or unsupervised cheating detection module 3104. According to the supervised fraud detection module 3102, for example, the presented input sentence, the resulting translation, the existing translation known to be true, the user's current certainty score, and the translator over time. In a user interface having fields such as graphs showing variations in certainty scores, a reporting tool may show the output from each user. In reviewing a translation, a human teacher can accept or reject the translation, thereby adjusting the user's certainty score. If the cumulative report shows incorrect behavior, the teacher can remove the user (can revoke the user's translation authority). Removing a user or revoking a user's translation authority may be performed using the translation authority module 3106.

  Alternatively or additionally, the fraud detection module 3100 may utilize an unsupervised fraud detection module 3104. According to the unsupervised fraud detection module 3104, the accuracy of the translation can be measured using various metrics such as WER (word error rate) and BLEU (machine translation accuracy metric that compares machine translation with a good quality reference translation). Can be calculated using. Certainty in user translation capabilities can be checked for changes or variations (eg, rising or falling). Similar sentences presented to one translator can be presented to other independent translators using the system. Reliability between translators can also be calculated. For example, through random sampling, social network analysis (for example, checking whether two translators are socially connected or have no prior relationship), and chat sessions and / or By detecting repeated interactions between users in online games, collusion between translators can be avoided. Two users who regularly interact together online (eg, in an online game or chat session) may be more likely to engage in collusion. In some embodiments, item response theory (ie, theory and test theory used in linguistic psychology) is used to enhance the measure of translator certainty by translator ability. Fraud detection can be performed using item response theory to perform unsupervised fraud detection in a translation enhancement system with an incentive mechanism. Item response theory defines how translator accuracy can be measured against peers and against themselves to measure consistency over a period of time. In this way, deviations from the standard can be identified. Reliability between translators can also be calculated by presenting the same sentence to a translator again after a set period of time. Various thresholds in reliability and translator's certainty can be set, and if the translator's certainty falls below such threshold, the translator uses the translation authority module 3106 to May be removed or blocked (eg, the user's translation authority may be revoked). In some implementations, translations from the high certainty system are added to the translation versus vocabulary.

  FIG. 31B includes a flowchart of a method 3110 for detecting fraud in incentive translations in accordance with an embodiment of the present invention. The method includes selecting a mixture of old training data and new training data (step 3112). Old training data includes one or more old text messages with known correct translations into different languages. The new training data includes one or more new text messages whose correct translations into different languages are unknown. A plurality of respective requests are sent to the user's client device at different times (step 3114). The request includes (i) a request to the user to translate old training data and / or new training data, and (ii) an incentive for the translation. After sending the specific request, a translation is received from the client device for the old training data for the specific request (step 3116). The received translation is compared to the correct translation for the old training data (step 3118). The accuracy of the received translation is determined based on the comparison (step 3120). Next, the certainty score is updated for the user based on the translation (step 3122). The certainty score represents the likelihood that the user will later provide an accurate translation of the text message into a different language.

  In various embodiments, the systems and methods described herein utilize speech translation or speech recognition technology to convert one language audible speech to another language for users of group voice chat systems. translate. For chat terms, a speech-text transcription system transcribes a user's chat terms into text, which is then converted into plain language (eg, non-chat terms) and translated into a foreign language Can be realized. Thereafter, a final conversion is performed to create foreign language chat terms, which are then output to the end user through a foreign language text-to-speech system. The system and method preferably uses state-of-the-art speech recognition techniques and statistical machine translation techniques with very fast decoders.

  FIG. 32 is a schematic diagram of a group chat system 3200 that allows groups of people speaking different languages 3202 to interact with each other using chat terms. As described herein, system 3200 may identify languages spoken by people participating in group chat system 3200. If the first user 3204 wants to send an audible chat term message to the second user 3206, the first user 3204 sends the audible chat term message 3208 in a first language (eg, English) to a user input device (eg, a chat client system). To the microphone). The speech recognition module 3210 converts the audible chat term message into a chat term text message 3212 in a first language. Conversion module 3214 is used to convert chat term text message 3212 into plain language (eg, non-chat term) first language text message 3216. The translation module 3218 is then used to translate the plain language text message 3216 into a corresponding plain language text message 3220 in a second language (eg, French). A conversion module 3222 is then used to convert the corresponding plain text message 3220 into a corresponding chat term text message 3224 in the second language. As those skilled in the art will appreciate, the conversion module 3222 may be the same as or form part of the conversion module 3214. A text-to-speech module 3226 is then used to convert the corresponding chat term text message 3224 in the second language into a corresponding chat term audible message 3228. Finally, the corresponding chat term audible message 3228 is delivered to the second user 3206 using an output device (eg, a speaker on the second chat client system).

  In various embodiments, the speech recognition module 3210 may use a hidden Markov model, dynamic time warping (DTW) based speech recognition to convert an audible chat term text message 3208 into a chat term text message 3212. And / or a neural network may be utilized. Similarly, the text-to-speech module 3226 may use speech synthesis to convert a corresponding chat term message into a corresponding chat term audible message. As will be appreciated by those skilled in the art, speech synthesis is concatenative synthesis (eg, unit selection synthesis, diphone synthesis and / or domain-specific synthesis). , Formant synthesis, articulatory synthesis, HMM-based synthesis, and / or sinusoidal synthesis.

  An important aspect of creating such a speech processing system involves collecting speech samples from multiple accents and dialects for languages that can be processed. The nature of the audio data may include chat language and plain language formats for each language to maintain the system's relevance to the field to which the system corresponds. The feedback mechanism provided with the incentive described herein can be used to transcribe these speech samples, which are then passed through the speech recognition module 3210 and / or the text-to-speech module 3226. Can be used for training. If sparse, field adaptation techniques can be used to replace the data points. This may be necessary in the case of a chat term speech sample where data tends to be sparse. For example, voice data collected in the gaming field (eg, for online games) can be replaced with plain language data that is fully available data. Field adaptation is preferably a rule that manages small speech fluctuations from a chat term in a given language-plain speech (eg, conversion from chat term to plain speech in a given language or plain term to chat term Identifying rules that govern the conversion to). A plain phrase that does not have a voice sample in the corresponding sentence of the chat term can be converted into a chat term using these domain-level rules. The user feedback loop may tune the acoustic model parameters (eg, for speech recognition module 3210 and / or text to speech module 3226) to a level that limits the acoustic model field and thus makes it more accurate. Can be used. For example, if the speech recognition module 3210 consistently has difficulty with a particular accent, additional audible samples of various words at that accent may be provided to the system (eg, by the user). This will assist the speech recognition module 3210 to learn how to better recognize words spoken with the accent.

  As described above, the system and method embodiments described herein are used to translate text or chat messages from a group chat environment into different languages. Archiving such translated chats can lead to a great deal of text in different languages remaining in the repository.

  Referring to FIG. 33A, in some embodiments, the chat history module 3300 can retrieve the chat history when the chat history is browsed by the user to reduce storage requirements and facilitate review of the chat history by the user. Used to translate in real time. Chat history module 3300 includes a chat storage module 3302 (eg, a register or other storage device) for storing chat histories from various users. Chat history module 3300 further includes a chat history conversion module 3304 that converts the text message before and / or after the text message is translated into a different language. For example, chat history conversion module 3304 may perform real-time conversion of chat history text messages from chat terms to formal or plain language. In some embodiments, the chat history conversion module 3304 is the same or similar to the conversion module 208. Chat history module 3300 further includes a chat history translation module 3306 that can be used to perform real-time translation of chat history text messages (e.g., formal or plain) into different languages (e.g., French to English). Chat history translation module 3306 can be or include other modules or components described herein, such as language module 206 and / or conversion data store 210.

  Once the user has reviewed the chat history, the converted and / or translated text generated by chat history module 3300 may be deleted or removed from memory. This reduces storage requirements for the system and method. If the user later wants to review the chat history, the chat history module 3300 can be used again to translate and translate text in the chat history as needed.

  In some embodiments, the chat history module 3300 translates the chat history for the user in real time. Chat history module 3300 receives a request from a user to review the history of text messages from a chat session. Chat history module 3300 receives a history of text messages including text messages in a plurality of languages from chat history storage module 3302. Chat history conversion module 3304 and chat history translation module 3306 are then used to convert and / or translate the initial portion of the chat history into the language used by the user as needed. After browsing the translated first portion of the chat history, the user may want to browse a different portion of the chat history. Thereafter, chat history module 3300 may receive a request from the user to view different portions of the history of the text message. Thereafter, the chat history conversion module 3304 and the chat history translation module 3306 are used to convert and / or translate different parts of the chat history to the language used by the user, as needed. Chat history module 3300 preferably performs real-time conversion and / or translation as the user scrolls through the chat history.

  In some cases, scrolling the chat history presents scale and data storage issues. Providing infinite scrolling of chat history presents the problem of fast real-time access of data across multiple databases and multiple users. This can be done by performing multiple processes in parallel that fetch historical messages from all users present in the chat room. Translations on these messages and associated chat transformations can be done in parallel as the messages are fetched from data storage. The resulting output realized by the end user is the output of a seamless transition from one screen of the chat to the next screen that has already been looked up from the database. This is because an infinite number of systems and methods described herein cannot have limitations on data storage and parallel computation can be reused between previously performed processes. You can continue on the screen.

  FIG. 33B is a flowchart of a method 3310 for translating a chat history in real time according to an embodiment of the present invention. Method 3310 includes receiving a request from a person to review a history of text messages from a chat session (step 3312). The history preferably includes text messages in multiple languages and from multiple users. At least two parallel processes are executed (step 3314). Each parallel process (i) receives or selects a text message generated by a respective user of a chat session (ie, a text message that forms at least part of the history of the text message), and (ii) the text message Translating to the target language. Translated text messages from multiple parallel processes are provided to a person's client device (step 3316). A request is received from the person to review different parts of the text message history (step 3318). Steps 3314 and 3316 are repeated for different parts of the text message history.

  In some cases, users of the systems and methods described herein may wish to avoid interacting with other users in a group chat or gaming environment. In previous chat systems, banning and silencing chat users is typically handled by a chat server administrator or moderator. However, embodiments of the systems and methods described herein allow a user to have direct control over who can send chat messages and / or chat contact invitations to the user. To do. For example, User A may invite User A to no longer see communications from User B in any chat room and / or User A no longer invites Personal Chat contacts from User B (ie, one-on-one chat). User B may be allowed to block so as not to receive.

  In various implementations, an alliance is a group of players in a game (eg, a multiplayer online game) that can be grouped together as a unit to improve game play. Each alliance preferably has its own chat room where members of the alliance can speak to each other or send text messages. This presents the need to sometimes block certain users from the Alliance chat room.

  FIG. 34A includes a screenshot of a user interface 3400 that allows a first user of a gaming system to block communication from a second user of the gaming system, according to an embodiment. As shown, the first user selects a management settings icon 3402 (eg, by tapping the touch screen), which opens a settings window 3404. Thereafter, the first user selects the “Block from Alliance” button 3406 on the setting window 3404. A message window 3408 appears to notify the first user that future communications from the second user will be blocked. The second user may be added to the list of other users blocked by the first user. The first user may have the option to edit this list to add or remove users from the list. For example, referring to FIG. 34B, the next time the user selects the management settings icon 3402, the settings window 3404 may include unblock from the alliance button 3410. If the first user selects unblock from the alliance button 3410, future communications from the second user may be unblocked, so as to notify the first user that such communication has been unblocked. A message window 3412 may appear.

  In some cases, system complexity is introduced or reduced by the scale at which blocking and unblocking is performed. Parallel computing can provide the flexibility to perform blocking and unblocking in real time without the time lag drawbacks found in conventional systems. For example, parallel processing may be used to translate and / or convert text messages in a text message chat system. A separate parallel process may be assigned to each user of the chat session and / or each language used for the chat session. Such parallel processing may simplify the task of blocking and unblocking users. For example, separate parallel processes may be removed or added from the chat system when a user is blocked or unblocked, respectively.

  FIG. 35 is a flowchart of a method 3500 for blocking a user from a chat session, which includes providing a text message chat system to a plurality of users of an online game (step 3502). A request is received from the first user of the text message chat system to block the second user of the text message chat system (step 3504). After receiving the request, a text message from the second user is prevented from being displayed to the first user (step 3506). In some cases, text messages in a chat session are translated and / or converted using the systems and methods described herein. A parallel process may be used to perform translation and / or conversion of text messages. For example, a separate parallel process may be assigned to handle the translation and / or conversion of text messages for each particular user in the chat session and / or for each language included in the chat session.

  Automated translation services are not always accurate and can sometimes benefit from human intervention to correct certain errors. In some implementations, the translation systems and methods described herein allow a user to identify translation errors and provide corrections to correct these errors. For example, a bilingual user or a foreign language user (eg, a French player in an online game) may browse a chat window and see an inaccurate translation (eg, a translation into or out of French). The user may submit a correction proposal for the incorrect translation and may be rewarded for submitting the correction (eg, by in-game currency or a virtual item).

  In one implementation, the original text message and the corresponding translation are displayed on a single screen, thereby providing an opportunity for those who are proficient in the language to provide immediate feedback on the translation. For example, the user may recognize translation errors and select an option to submit a corrected translation. The user can then enter and submit the modified translation and receive a reward once the modified translation is approved. In submitting the modified translation, the user may be prevented from submitting an additional modified translation for the original message. Thus, the user may not be able to get multiple rewards from a single incorrect translation.

  In some cases, the system and method cannot translate the original message because the original message was not entered correctly by the user. For example, FIG. 36A shows an original Spanish message 3602 representing “Eres el peor!”. An automatic English translation 3604 of this message is shown in FIG. 36B and represents “You are the best!”. Referring to FIGS. 36C and 36D, the user may recognize that the translation has become inaccurate because the original message was not entered in the appropriate Spanish. To respond to this error, the user may select a “correct translation button” 3606 so that a modification window 3608 may be opened in which the user can enter modifications for the original message. Referring to FIGS. 36E and 36F, in this case, the user inputs “Ustedes son los mejores!” In the modification window 3608 and selects the submit button 3610. A confirmation window 3612 appears to notify the user that the submission will be processed. When the confirmation window 3612 is closed, the user returns to the original chat page.

  With reference to FIGS. 37A and 37B, a user interface 3700 is provided that allows a user to review translation modifications received from other users. Users considering translation modifications may be rewarded for their efforts and may be able to select the specific type of reward they receive (eg, virtual goods or currency for online games). In general, after a translation fix is submitted by a user, other users may determine whether the fix is better than the original translation and any other translation fix submitted by other users. If the user's translation is determined to be the best translation, the user can receive an award and the user's translation can be added to a translation dictionary (eg, translation data store 210). Users who participate in determining various translations may also receive rewards. However, such a reward can only be given to a user who selects the translation modification best chosen by all of the judges.

  In general, by allowing users to submit translation correction proposals and to determine other users' submissions, the system and method take advantage of the feedback that the user voluntarily gives. The data collected in this process, once approved, can be used to modify translation cache entries, thereby improving the overall translation capabilities of the systems and methods described herein. This may ensure that the correct translation is indicated in the future when the original message is submitted again for translation.

  In a typical implementation, there are two types of users, monolingual users and bilingual users, who can submit and / or determine translation corrections. Bilingual users can generally understand sentences in the original language and provide more accurate translations in different languages. In contrast, a monolingual user may not understand the original language phrase, but may still consider the translation (presented in the language of the user's device) and submit corrections in exchange for rewards. Translations from the two types of users tend to be different in content, with bilingual users generally providing more accurate translations. The system and method can preferably determine or detect whether the user is monolingual or bilingual and the user feedback can be weighted according to the determination. For example, a user may be able to identify themselves to the system and method as monolingual or bilingual.

  In some situations, most users are monolingual and speak the same language (English). A large supply of people who speak a language typically has more users submitting translation corrections for that language, and generally less demand for translation corrections to or from that language Become. Users can be rewarded according to the demand for translation corrections to stimulate the supply of translation corrections for other languages. For example, if the majority of users speak a language and there is no shortage of translation corrections given in that language, such users will receive a smaller reward for submitting translation corrections (eg, 75% of the nominal amount). ). At the same time, a small number of users who speak different languages may receive a greater reward (eg, 125% of the nominal amount) because of the greater demand for translation corrections in that different language.

  The number of translations that a user modifies during a given period (eg, one day) may or may not be limited. For example, if there is no reward for submitting corrections, there may be no limit on the number of translation corrections. On the other hand, if the user is rewarded for such submission, during that period, the user may be allowed to submit a limited number of translation modifications. Such a restriction may result in an unfair advantage in underlying games (eg multiplayer online games) by receiving excessive rewards for bilingual users or users who tend to submit numerous translation corrections Can prevent.

  In some cases, feedback for inaccurate translations may be received from only a small number of users (eg, two or three users), thereby determining the accuracy of the translation submission and automatically rewarding it. It can be difficult to produce. For example, chat occurs in a continuous stream, and many users can concentrate by chatting with other users and / or playing the underlying game, and less concentrated on submitting translation corrections do not do. In addition, users can select chat based on what they see in their windows, and few users can select the same chat. Thus, if more than one translation correction is received, the correction proposal may be made available to other users to make a decision to obtain consensus for the correct translation in return for a reward.

  Rewards for submitting translation corrections can be given to the user according to a raffle system. In such a system, not all submissions are rewarded, but can be randomly distributed so that users submitting more modifications are more likely to get rewards. Such an approach may allow a player to achieve an unfair advantage over other users because of his ability and / or desire to translate messages rather than his own ability or commitment of the underlying game Reduce the possibility.

  In addition to allowing the user to correct bad translations, the user can also provide feedback regarding misdetected languages, obscene words that are not filtered, and specified entity detection Can be. For example, viewing the original message and the translated message, the user may recognize that the automatic translation system has improperly detected the original language. The user can then notify the system about this language detection failure in exchange for possible rewards. Similarly, the user may be able to notify the system about any obscene language that appears in the message, so that the system filters or removes such obscene language from future messages. Enable. The user may further be able to inform the system about specified entities that appear in the message, such as company, brand, trademark, etc. This may allow the system and method to recognize when specified entities appear in the message and ensure that such entities are properly specified and / or identified.

  In general, translation corrections submitted by the user require careful evaluation to ensure that the user is rewarded only for correct corrections. This improves the overall accuracy of the system and prevents the user from cheating by submitting unauthorized modifications. In some implementations, the accuracy of the translation correction can include word-based features, language-based features, and other features (eg, word alignment match features) to prevent users from misusing the system. Automatically evaluated. A part of speech (POS) based language model can be used to check a sentence for grammatical accuracy. In addition, some users may submit translation corrections that are grammatically correct but have nothing to do with the original message. For such cases, the word alignment match analysis feature may be useful and may be implemented as a periodic process to approve and / or reject the user's submission. A machine learning approach may be used to enable sparse user feedback in the translation systems and methods described herein.

  Table 2 shows an example of translation correction proposals submitted by a user according to an embodiment of the present invention. In these examples, the original message in the source language is “aaa bbb ccc” and the correct translation in the target language is “xxx yyy zzz”. The column labeled “Indicated Translation” contains an example of the initial translation proposed by the automated system described herein.

Table 2. Examples of User Modifications and Preferred Results As shown in Table 2, when a user submits a correct and improved translation, the user's submission should be approved and the user can receive an appropriate reward. However, if a user submits a low quality or incorrect translation (eg, a random message), the user's submission should be rejected and no reward should be given to the user. The system and method preferably approves or rejects such examples as shown in the “Status” column of this table.

  In some embodiments, translations of the original message are classified according to whether the translation is appropriate for the original message. The classification can be treated as a binary classification task where features are extracted from the translation and the original message. Classification techniques can be used to ensure that translation corrections submitted by the user are accurate. For example, in some cases, the majority-based validation described herein is not preferred due to the small number of responses (eg, 1-3) that can be received for inaccurate translations. Classification techniques can also be used to identify and / or respond to hash collisions that appear in cached translation data. For example, about 10% or more of the translation entries in the data table can be corrupted by hash collisions.

  Referring to FIG. 38, in various implementations, translation accuracy is evaluated using a translation accuracy module 3800 that includes a word-based feature module 3802, a language-based feature module 3804, and a word alignment module 3806. . The word-based feature module 3802 is used to evaluate word-based features such as word counts, character counts, pictograms, numbers and / or punctuation marks. For example, if the translation is correct, the number of words in the original message is generally about the same as the number of words in the translation. Thus, if the number of words in the two messages differ by more than a threshold amount (eg, a factor of 2), the translation may be considered inaccurate or likely to be inaccurate. In one example, if the number of words in one of the messages (eg, translations) is 1/2 (or less than half) the number of words in other messages (eg, the original message), the word-based feature module 3802 can conclude that the translation is incorrect or likely to be incorrect.

  Another word-based feature that can be used to assess translation accuracy is the number of letters (eg letters and numbers) in the original message and translation. In general, if the number of characters in the original message is approximately the same as the number of characters in the translation, the translation is more likely to be accurate. The threshold amount can be used to determine when the character counts in the two messages are significantly different. For example, if the translation has more than 3/2 characters of the original message, the word-based feature module 3802 may conclude that the translation is likely to be incorrect or inaccurate.

  Another word-based feature that can be used to assess the accuracy of a translation is an emoji that generally remains unchanged between the original message and the translation (eg, ideograms or smileys used in Japanese electronic messages). (Smiley)) count and order. Pictographs tend to fall within certain Unicode text ranges that can be used to detect them in a given sentence. Using this Unicode range, regular expressions can be used to identify or extract pictograms from both messages. For example, if the input contains three pictographs consecutively and the output contains only one pictograph, a difference is indicated between the input and the output. If the emoticon count and / or order is different between the two messages, the word-based feature module 3802 may conclude that the translation is incorrect or likely to be incorrect.

  An additional word-based feature that can be used to assess translation accuracy is an arbitrary number and punctuation count in the two messages. For example, numbers and punctuation marks, if present, can be identified or extracted in the original message and translation, and the length of the longest common subsequence (LCS) is determined between them after sorting. Can be. This length divided by the maximum length of the two messages gives a real value for this word-based feature. In general, real values provide an indication of the percentage of duplicate numbers and punctuation in two messages. Experimental results show that for this particular feature, better results are obtained using real values rather than binary values. For example, an English input sentence “I am going to meet you at 4:30 Cya !!” may have an equivalent output of “Je vais vous recontrer a 4:30 Au revoir !!”. When extracting punctuation and numbers, “4:30!” Is obtained for both English and French versions. In this case, the LCS is 6 (unit is character), and the maximum value of the length from the English version and the French version is 36 (unit is character). The resulting real value for this word-based feature is 6/36 = 0.167.

  Relying solely on word-based features may be insufficient for assessing translation accuracy. For example, a user may be able to deceive at least some of the word-based features by submitting translation corrections where each word of the original message is replaced with a dummy word (eg, “xxx”). This creates a fraudulent correction with the same number of words and characters present in the original message.

  To circumvent this problem, translation accuracy module 3800 may use language-based feature module 3804 to evaluate language-based features in addition to or instead of word-based features. For example, in one embodiment, words present in the original message and translation are identified (eg, using an open source POS tagging machine) to identify parts of speech (POS) (eg, verbs, nouns, adjectives, etc.) in the two messages. Tagged). Each word in the message can be tagged according to the part of speech with a different number of tags, using different tags set for each language. For example, a sample sentence “The device is easy to use” can be tagged with a POS tagging machine, “The_DT device_NP is_VBZ easy_JJ to_TO use_VB”, indicating the part of speech of each word in the sentence. In this case, the tag is a determiner (DT), a noun phrase (NP), a singular present adjective verb (VBZ), an adjective (JJ), To (TO), or a single verb (VB). The main subject tag for this purpose is typically a verb, followed by an adjective and an adverb.

  In some cases, the original message and translation are tagged separately (eg, using a POS tagger), and the resulting tag counts for each message to identify the number of verbs, adjectives, adverbs, etc. in each message. Is done. Due to the different types of verbs used in each language (eg legal verbs, indefinite verbs, past adjectives, futuristic verbs, etc.), the simplified verb tag VB maps for all types of verbs in each language. Can be obtained using. For example, an English verb part-of-speech tag may be mapped to a singular verb tag VB as follows: That is, 'VBD' (verb, past tense) => 'VB', 'VBG' (verb, verb noun) => 'VB', 'VBN' (verb, past participle) => 'VB', 'VBP' (Verb, non-third-person singular current) => 'VB' and 'VBZ' (verb, third-person singular current) => 'VB'. POS tags in tagged messages can be replaced with this simplified POS tag set.

  After simplifying the POS tag, the number of verb tags VB can be counted in both the original message and the translation. Ideally, the number of verbs in each message should be the same, with some exceptions. For example, “was sleeping” in English translates to “dormais” in French. The English POS tagging machine can tag “was” and “sleeping” as two different verbs, while the French POS tagging machine can tag “dormais” as a single verb. . Verbs such as “is”, “was”, and “can” are known as auxiliary verbs in English. Other languages may not have an equivalent to these auxiliary verbs, and instead a single verb may be used as a replacement. In view of such differences in verb usage between languages, the system and method may use a threshold (eg, 2 or 3) for the difference in the number of verbs between the original message and the translation. For example, if the difference between the number of verbs in two messages is greater than 2, the language-based feature module 3804 may consider that the translation is likely to be inaccurate or inaccurate. This threshold value of 2 has been found to produce reasonable results through trial and error. Other parts of speech (eg, adjectives and adverbs) can be counted and compared between the two messages using one or more additional thresholds.

  However, in some cases, the user can deceive this translation accuracy check by simply copying and submitting an existing translation as a modification to the translation. In that case, the submission may be classified as a valid modification, but the user may not be rewarded for the submission. In some cases, a user may simply change the case of some words in an existing translation to create and submit a valid correction, and the user deserves the reward and submits the submission. You can be rewarded for things. Thus, in some embodiments, the systems and methods determine whether an existing translation and a user submission are the same. If the existing translation (including case and capitalization, for example) and the user submission are the same, no reward can be given to the user.

  In one embodiment, the POS tag check is used to identify when the automatic translation system did not correctly identify the language of the original message. For example, the language of the original message may be detected incorrectly when the user's translation correction passes the word count check, but may fail in the POS tag check. Furthermore, there is a possibility of incorrect language detection if the number of verbs is equal to 0, or if all tags are nouns in one message and not in the other message. For example, the original Spanish message is “

Can be represented. However, if it is detected that the language is English, it is likely that the English POS tagger will not be able to tag the message, and by default all words can be tagged as nouns. The output of an English POS tagging machine can be, for example:

As a comparison, the output of a Spanish tagger for the same original message can be as follows:

The tags “NN”, “RB”, and “PPX” refer to the noun (s), adverbs, and possessive pronouns, respectively.

  Thus, in some cases, the original message and the part of speech of the translation are compared to determine if the language was properly identified in the original message. In general, if one of the messages (eg, translation) is tagged as having a non-zero number of verbs and the other message (eg, the original message) is tagged as not having a verb, a language detection failure will occur. More likely to occur. Furthermore, if all the words in one message are tagged as nouns, while other messages have some type of POS tag (eg nouns, verbs and adjectives), there is a higher chance of language detection failure .

  In various embodiments, the accuracy of the translation is assessed by identifying and considering the original message and proper nouns in the translation. In general, if the translation is correct, the proper nouns (eg, people's names and city names) are the same in the translation and the original message. Thus, comparing two messages and filtering common words that remain untranslated may be useful as a feature to identify pure translations. In some cases, the presence of such untranslated proper nouns can help improve translation accuracy, but the absence of untranslated proper nouns can give any information about translation accuracy. Absent. If the proper noun is identified in the original message rather than in the translation, the accuracy of the translation can be considered likely to be inaccurate or inaccurate. Penalties can be added to the score of the real value returned for this proper noun feature, thereby helping to identify any bad translation and improve the accuracy of the translation. For example, if the proper noun is inconsistent between two messages, the accuracy score for the translation can be reduced by a penalty.

  Alternatively or additionally, the accuracy of the translation can be assessed by analyzing and comparing the grammar in the original message and translation. By working in multiple languages, it can be difficult to parse the tree for all languages in order to understand the grammar of the sentence. Messages are often written in chat languages that follow different grammars as compared to plain or formal speech in their native language.

  Thus, a sentence can be tagged with a POS tag to build an N-gram language model for the POS tag to recognize patterns between chat language grammars, thereby approximating the underlying grammar structure. I will provide a. An n-gram can be defined as a set of n consecutive words. These n-gram models can be typical for a given language and / or used to represent n consecutive words in a given language. In one implementation, the word-based n-gram method extends to part-of-speech based n-grams. In other words, a shallow method of parsing a sentence in which words in the sentence are tagged by a POS tagger can be used. In one approach, the BLEU score is calculated for the POS tag rather than the actual text.

  A trigram (3 gram) language model can be created on POS-tagged sentences for each language. For example, the sentence “The device is easy to use” has a POS tagged output of “The_DT device_NP is_VBZ easy_JJ to_TO use_VB”. The word-based trigrams in this sentence are {The, device, is}, {device, is, easy}, {is, easy, to}, {easy, to, use}. The corresponding POS-based trigrams are {DT, NP, VBZ}, {NP, VBZ, JJ}, {VBZ, JJ, TO}, {JJ, TO, VB}.

  A trigram with a higher probability can be used to indicate a partial structure of the grammar. For example, a trigram language model built on a POS tag may have a probability associated with each trigram. The probability can be calculated as the ratio of the number of times a given trigram has occurred in the text corpus compared to all trigrams in the same text. Grammatic trigrams often tend to be repeated, and thus have a higher probability (also known as a language model score). Thus, if a message receives a higher score on this language model, the message is more likely to be grammatically correct. This score can be useful to detect when a user types a spam message to get rewards. The score can also be useful in determining when language detection has failed. For example, sentence scores in the wrong language can be even lower because a separate model can be used for each language. The score can also be useful to detect when translation quality is good. For this purpose, separate models can be trained for human translation and machine translation.

  In certain embodiments, the language model is trained using translations that have been validated as accurate. A trigram model can be built on the POS tag.

  An inherent problem with any sized n-gram is the lack of all possible hypotheses. In such a case, a backoff method is employed in which n-1 gram and n-2 gram are identified. For example, if an unknown POS trigram such as {DT, NP, JJ} is found, the model is whether the bigrams {DT, NP} and {NP, JJ} have a language model score that indicates grammatical nature. Can be retroactively checked. If the bigram has no probability (or if the probability is too low), another backoff can be made to check the unigram language model score for {DT}, {NP}, {JJ}. All three models are further linearly interpolated with more weight on the trigram model, less weight on the bigram model, and less weight on the unigram model. Can be grouped by.

  The most frequently occurring trigrams of POS tags for chat English are <IN> <VBD> <PP> = 1.0, <FW> <NN> <IN> = 1.0, <DT> <WP> <VBP > = 1.0, and <RB> </ Sl> </ S2> = 1.0. A score of 1.0 indicates that there is a 100% probability that a given trigram sequence is grammatical at all times it occurs. In general, chat languages use more pronouns starting with “Wh” followed by a verb, which is understood by <DT> <WP> <VBP>. People also tend to end chat language sentences with adverbs or adjectives, as in “You are cool” or “This is awesome”, which is understood by <RB> </ S1> </ S2>. , S1 and S2 are sentence end tags. Thus, these trigrams can be used to recognize at least some structure of the underlying grammar in each language. Since language models are built for all languages of interest, the models can be saved in JSON format and loaded immediately at any time.

  In some implementations, after the message is POS tagged, the system and method may count the number of trigrams in the message that match the existing trigram language model. Each trigram in the model may have a probability score associated with it, and for each trigram in the message, the corresponding score of the trigram is identified in the model. In some cases, if the score is higher than a threshold (eg, 0.05), the trigram is counted as a match. Otherwise, the trigram is not counted as a match. The system and method can calculate the number of trigram matches relative to the total number of trigrams in a sentence, and this ratio can be used as a feature of real values to assess translation accuracy. For example, a trigram of {easy, to, use} that can occur frequently in grammatical text can have a high probability score (language model score) of about 0.68. In contrast, the {easy, use, to} non-grammatical trigram may have a smaller probability of occurrence of about 0.04. Compared to a defined threshold of 0.05, the non-grammatical trigram can be filtered, and the number of trigrams above the threshold can provide a quantitative value for the grammatical nature of the text.

  After obtaining a POS tagged message, the probability of a sentence can be calculated using a trigram language model. In one embodiment, the log probability of each trigram in the sentence is determined and the sum of log probabilities is calculated. This sum is then divided by the number of words in the sentence to get a score for that sentence. The score can be used as a feature of real values to assess translation accuracy. The loggram probability of a trigram is preferably calculated as a linear interpolation of trigram probability, bigram probability and unigram probability. For example, in the sentence “The device is easy to use”, the POS tagged output is “The_DT device_NP is_VBZ easy_JJ to_TO use_VB”. The POS-based trigrams for this sentence are {DT, NP, VBZ}, {NP, VBZ, JJ}, {VBZ, JJ, TO}, and {JJ, TO, VB}. Each of these trigrams has a probability of occurrence in a given language corpus. Assuming these probabilities are 0.12, 0.44, 0.32, and 0.89 for each trigram, the combined score for the grammatical nature of the sentence can be calculated as a log probability. In this case, the log probability is calculated as log (0.12) + log (0.44) + log (0.32) + log (0.89), which is equal to −1.82. On a relative scale, this log probability provides a numerical representation of sentence grammar.

  In addition to, or instead of, the word-based and language-based features described above, the translation accuracy module 3800 may evaluate word alignment between the original message and the translation. A word alignment module 3806 may be used. To generate a list of potential word alignment pairs, a translation accuracy check algorithm is performed on the database using only word-based features, and a bilingual corpus having translation pairs with probability values> 0.90 is obtained. Extracted. This indicates that only good quality translation message pairs are filtered to create a bilingual corpus. 100K sentences were collected for English and French pairs and English and Spanish pairs. The bilingual corpus for these 100K sentences was supplied to a statistical machine translation toolkit (ie GIZA ++) to extract word alignments. The toolkit extracted approximately 25-30k word alignment pairs and associated probability scores for these pairs.

  Given that there are usually multiple word alignments per word, it may be beneficial to select only those alignments that have a probability score greater than a certain threshold (eg, 0.01). However, even with the threshold, more than one alignment per word can be obtained, most of which are typically due to spelling errors or the same word in different tenses (eg, past or future). A sample word alignment between English and French is shown in Table 3. Separate word alignments can be obtained for both possible sequences of the two languages (eg, English to French and French to English). Thus, two word alignment files can be extracted per language pair. The word alignment for the source language (ie, the language of the original message) relative to the target language (ie, the language of the translation) may be referred to as the source alignment, while the word alignment for the target language relative to the source language may be referred to as the target alignment.

Table 3. Typical word alignment between English and French The source alignment and target alignment can be loaded into two separate files. For each word in the original message that is also present in the source alignment, the system and method determines whether at least one corresponding word is present in the translation and also in the target alignment. The same process is then applied to the translation. Finally, the percentage of words found in the word alignment file is returned as a feature to assess translation accuracy.

  In one implementation, word alignments are extracted for language pairs that include English as one of the languages. For example, a language pair is a combination of English and one of Spanish, French, Polish, Portuguese, Dutch, German, Danish, Swedish, Turkish, Italian, and Russian. There may be a total of 11 language pairs and 11 × 2 = 22 word alignment files. For language pairs that do not include English (eg, translation from French to Russian), English can be used as an intermediate language to extract alignments. For example, when enabling a French to Russian translation, French-English may be used to extract word alignments from the original message, and Russian-English may be used to extract word alignments from the translation. . The intersection of these two sets gives the percentage of matches between word alignments in both messages. This method can be extended to all language pairs.

  In various embodiments, user certainty is calculated to provide an indication of whether the user's translation submission can be trusted. Apart from the other approaches discussed herein, the user may be more or less trusted based on the user's history of translation modifications. The number of translations modified and the number of translations awarded can be stored in a data table for various users. Thereby, the percentage of corrections made by the player can be calculated and translation corrections can be approved based at least in part on the certain user's certainty threshold. This makes it possible to separate spammers from pure players that easily correct translations.

  FIG. 39 is a flowchart of a method 3900 for correcting translation errors, according to an embodiment. The method 3900 includes providing a text message chat system to a plurality of users of an online game (step 3902). An original text message is received in a first language from a first user of an online game (step 3904). An initial translation of the original text message is generated in the second language (step 3906). The original text message and the initial translation are provided to the second user of the online game (step 3908). For example, the second user may view the two translations together or separately on the display of the client device. A translation correction is received from the second user to accommodate an error in the initial translation (step 3910). The method 3900 may further include identifying the most accurate translation correction from a plurality of translation corrections (ie, including translation corrections from a second user) (step 3912). Alternatively or additionally, the method 3900 uses at least one of a word-based feature, a language-based feature, and a word alignment feature to assess the accuracy of the translation correction from the second user. (Step 3914).

  The word-based features and language-based features described above (eg, four word-based features and four language-based features) can be fitted using a linear regression model. After training, the model preferably returns the number of real values for each translation pair, and a threshold can be used to classify each translation pair as good or bad. For example, if the feature returns a numerical value of x1, x2, x3 ... x8, the regression equation can be y = a1 * x1 + a2 * x2 + ... + a8 * x8, where a1, a2,... A8 models a linear regression equation Is a coefficient obtained from the above, and y is an output value. The preferred value for threshold y was found to be 0.65 after accuracy and reproducibility experiments using ROC curves.

  After adding the word alignment based features described above and performing linear regression again on the word based features and language based features, the preferred threshold was changed to 0.76. In addition, the AUC value was increased from 0.853 to 0.976 by adding word alignment based features.

  Table 4 shows the regression coefficients obtained from 13k sentence training for each of the word-based features, language-based features, and word alignment features. The results in the table indicate that, after normalization, emoji features and character counts have small regression coefficients, meaning that these features were found to contribute little to assessing translation accuracy. .

Table 4. Regression coefficients for translation accuracy features Regression models were evaluated by 10-fold cross validation for 13k sentences in French-English pairs and Spanish-English pairs. Representative labels for the data were calculated using BING translation with some human supervision. Table 5 shows accuracy, repeatability, accuracy, and F-measure value in percentage for evaluation. The accuracy represents the ratio of true positive translation pairs among all translation pairs marked as true by our method. Reproducibility is the ratio of true positive translation pairs to all translation pairs known to be true pairs. Accuracy is the ratio of the sum of the results marked as true positive and true negative to the total test set size. The F scale is a harmonic average of accuracy and reproducibility. These metrics can be used in classification tasks to measure system performance and reliability. 13k sentences were used as a training set and 400 hand annotated sentences were used for testing. Because the test set was small, the number for the test was less than the number for the 13k sentence.

Table 5.1 Results of translation accuracy observation using 13,000 sentences Table 6 shows the results of 10-fold cross validation for a 13k sentence data set, W refers to the use of word-based features, L refers to the use of language based features and A refers to the use of word alignment features. These results show that word-based features help improve accuracy and word alignment features help improve reproducibility significantly. Language-based features give a slight boost to both accuracy and repeatability. In general, the reproducibility indicates how accurately bad decisions are detected from the total data set. The results in the table above show that the reproducibility is improved by adding word alignment based features. The accuracy indicates how accurately a good translation was predicted from the total translations marked as correct by the system. The results in the table show that accuracy is improved by adding word-based features.

Table 6.1 Results of 10-fold cross-validation for sentence data set of 13,000 Table 7 fits various word-based features, language-based features, and word alignment features with other machine algorithms, according to an embodiment. Shows the results. The results so far have been shown using linear regression techniques to tie different features together. There are machine learning algorithms that can be used to link variables (features in this context) together to produce better ensemble results than individual parts. Linear regression shows a single dimensional method for combining variables. In the machine learning algorithm literature, there are two-dimensional and multi-dimensional methods for combining variables. These algorithms were used to find a more optimal way of combining features used in the task of predicting good translation pairs.

  The results in Table 7 were obtained by combining features with various machine learning algorithms. The data set used contained 13k sentences, and the parameters were adjusted using a gridSearch algorithm. From the methods listed in the table, the gradient boosting classifier and the random forests method are ensemble-based methods, which explains why these methods gave better results. explain. Gradient Boosting Machine (GBM) takes longer to train, but GBM and random forest give very good results. However, training time is generally unimportant because the model needs to be trained only once.

Table 7. Results of fitting translation accuracy features with a machine algorithm The final translation accuracy check algorithm is tested against a provided test set of 3045 English-French sentence pairs. The results are shown in Table 8. The performance of WLAplain features is poor due to the fact that word alignments are extracted from plain language databases. Since the message is modified after a series of transformations, a sharp decrease in these results can be found. The word alignment has been extracted from the chat term database and some smoothing has been done on smaller sentences to avoid zero scores in the features. WLA shows the results for the chat term database. Poor accuracy due to the WLA feature indicates that many true translations have been rejected. Since the random forest was overfitting the results, the features were fitted with linear regression. In general, these results can be used as a basis for selecting the final set of features used in the algorithm. While higher accuracy is generally preferred, higher accuracy rewards more accurate translation pairs entered by the user, and high recall reduces fewer erroneous entries that are misclassified as correct Guarantee. According to the results in the table, the WLA feature set is desirable. A threshold of 0.75 can be selected for higher repeatability (eg, to get the least malicious entry marked as correct), and 0.68 if high accuracy is desired. A threshold can be selected.

Table 8. Results from Translation Accuracy Check Algorithm Although the present invention has been shown and described in detail with reference to certain preferred embodiments, it departs from the spirit and scope of the invention as defined by the appended claims If not, it should be understood by those skilled in the art that various changes may be made in form and detail.

Claims (35)

A computer-implemented method comprising:
Selecting a word or phrase from at least one data store associated with a translation failure from a first language to a second language of a message containing the word or phrase;
Selecting a user seeking user feedback for the translation failure based on the user's characteristics ;
Determining an incentive value to provide to the user in exchange for the user feedback based on characteristics of the word or phrase ;
It comprises transmitting a request for the feedback to the computing device selected the user, before Symbol method further
Receiving the user feedback from the computing device, wherein the user feedback includes a respective word or phrase of the first or second language, the method further comprising:
Storing the user feedback in the at least one data store;
Storing, in the at least one data store, information indicating that the user feedback is approved if the user feedback is approved;
Crediting the user's account according to a value of the incentive in response to the information being stored in the at least one data store .   The method of claim 1, wherein the failure is due to an actual failure in translation of the message.   The method of claim 1, wherein the failure is by a user flagging the message as potentially inaccurate. Features of the user certainty measure of the user, preferences of the previous SL user, and comprising said at least one of the user's language ability, according to any one of claims 1 to 3 the method of. The method according to any one of claims 1 to 4 , wherein the word or phrase comprises a chat term in the first language. The method according to claim 1, wherein the response includes a chat term in the second language. The method of any one of claims 1-6 , wherein the query includes a field configured to receive a text-based value. Wherein the request, the user includes a set of definitions preselected it is possible to select a definition of the word or phrase, the method according to any one of claims 1 to 7.   The set of pre-selected definitions includes at least one definition provided by another user in response to another request, the other request previously for the word or phrase from the other user. 9. The method of claim 8, wherein the method is previously generated to obtain user feedback.   The method of claim 9, wherein the other request includes another set of the preselected definitions from which the other user has selected the definition. If a plurality of unique user feedback responses are received , evaluating the user feedback to determine a user feedback corresponding to a user feedback response having the highest number of received among the plurality of unique user feedback responses. The method according to any one of claims 1 to 10 , further comprising: The method according to any one of claims 1 to 11 , further comprising determining suitability of the user based on the user feedback. Based on said user feedback, the further comprising the first language to update the conversion or translation of the word or phrase to the second language, according to any one of claims 1 to 12 the method of. If the previous SL user feedback is not invalid, or if the user feedback is correct, further comprising determining that user feedback has been approved, according to any one of claims 1 to 13 the method of. If in response to other requests for at least one previous user feedback provided by other users and precisely define the word or phrase, further comprising determining that said user feedback is approved, claims The method according to any one of claims 1 to 14 . The method according to any one of claims 1 to 15, wherein the incentive includes an in-game currency or an in-game item. The characteristics of the word or phrase include the complexity of the word or phrase, the importance of the word or phrase, the response method used by the user, the type of word or phrase, and the language included in the translation failure At least one factor for including method according to any one of claims 1 to 16 which is selected from the group consisting of a. A system,
Including one or more computers, the one or more computers comprising:
Selecting a word or phrase from at least one data store associated with a translation failure from a first language to a second language of a message containing the word or phrase;
Selecting a user seeking user feedback for the translation failure based on the user's characteristics ;
Determining an incentive value to provide to the user in exchange for the user feedback based on characteristics of the word or phrase ;
It is programmed to perform operations and transmitting a request for the feedback to the computing device selected the user, before Symbol least one computer is further
Programmed to perform an operation comprising receiving said user feedback from said computing device, said user feedback comprising a respective word or phrase of said first or second language, said 1 More than one computer
Storing the user feedback in the at least one data store;
Storing, in the at least one data store, information indicating that the user feedback is approved if the user feedback is approved;
Determining that the user feedback is approved;
A system programmed to perform an operation comprising: granting credit to the user's account according to the incentive value in response to the information being stored in the at least one data store . The system of claim 18 , wherein the failure is due to an actual failure in translation of the message. The system of claim 18 , wherein the failure is by a user flagging the message as potentially inaccurate. Features of the user certainty measure of the user, preferences of the previous SL user or at least one of the language capabilities of the user, according to any one of claims 18 to claim 20 system. The system according to any one of claims 18 to 21 , wherein the word or phrase includes a chat term in the first language. 23. The system of any one of claims 18-22 , wherein the response includes a chat term in the second language. 24. A system according to any one of claims 18 to 23 , wherein the query includes a field configured to receive a text-based value. 25. A system as claimed in any one of claims 18 to 24, wherein the request comprises a pre-selected set of definitions from which the user can select a definition for the word or phrase. The set of pre-selected definitions includes at least one definition provided by another user in response to another request, the other request previously for the word or phrase from the other user. 26. The system of claim 25 , which has been previously generated to obtain user feedback. 27. The system of claim 26 , wherein the other request includes another set of preselected definitions from which the other user has selected the definition. The operation is configured to determine a user feedback corresponding to a user feedback response having the highest number of received among the plurality of unique user feedback responses when a plurality of unique user feedback responses are received. 28. A system according to any one of claims 18 to 27 , further comprising evaluating. 29. A system according to any one of claims 18 to 28, wherein the action further comprises determining suitability of the user based on the user feedback. 30. The method of any one of claims 18-29 , further comprising updating a translation or translation of the word or phrase from the first language to the second language based on the user feedback. System. The operation, if the previous SL user feedback is not invalid, or if the user feedback is correct, further comprising determining that user feedback has been approved, one of claims 18 to claim 30 The system according to item 1 . The operation, when in response to other requests for at least one previous user feedback provided by other users and precisely define the word or phrase, further determining that the user feedback has been approved 32. A system according to any one of claims 18 to 31 comprising : The system according to any one of claims 18 to 32, wherein the incentive includes an in-game currency or an in-game item. The characteristics of the word or phrase include the complexity of the word or phrase, the importance of the word or phrase, the response method used by the user, the type of word or phrase, and the language included in the translation failure At least one factor for including a system according to any one of claims 18 to claim 33 which is selected from the group consisting of a. To improve language translation through feedback incentives given, a computer program that is stored in one or more storage medium, the computer program, the data processing device,
Selecting a word or phrase from at least one data store associated with a translation failure from a first language to a second language of a message containing the word or phrase;
Selecting a user seeking user feedback for the translation failure based on the user's characteristics ;
Determining an incentive value to provide to the user in exchange for the user feedback based on characteristics of the word or phrase ;
Executable by the data processing apparatus to perform operations including transmitting a request for the feedback to the computing device of the selected said user, said computer program is further said data processing device,
Executable by the data processing device to perform an action comprising receiving the user feedback from the computing device, the user feedback including a respective word or phrase in the first or second language. the computer program may further said data processing device,
Storing the user feedback in the at least one data store;
Storing, in the at least one data store, information indicating that the user feedback is approved if the user feedback is approved;
A computer executable by the data processing device to perform an operation including providing credit to the user's account according to the value of the incentive in response to the information being stored in the at least one data store. program.