JP7629415B2 - English correction device - Google Patents

Description

One aspect of the present invention relates to an English text correction device.

Conventionally, there is known a system that automatically judges whether an English translation created by a user for a question written in a language other than English (e.g., Japanese) is correct or incorrect (e.g., Patent Document 1). In the system described in Patent Document 1, when an English sentence (English translation, English composition) for a question is input by a user who is a learner, it is first judged whether the English sentence input by the user matches the English sentence of the correct answer data associated with the question. If they match, it is judged to be a correct answer, and if they do not match, it is judged to be an incorrect answer. In addition, in the above system, incorrect answer data including an incorrect answer and an explanation for the incorrect answer is stored in advance for each question. Then, if there is incorrect answer data that is judged to be an incorrect answer in the above judgment process and includes an incorrect answer that matches the English sentence input by the user, the explanation for the incorrect answer data is presented to the user.

JP 2008-197604 A

According to the system described in Patent Document 1, by preparing in advance for each question text incorrect answer data corresponding to several expected incorrect answers, it is possible to provide feedback on the content of the incorrect answer to the user who entered the English sentence corresponding to the incorrect answer. However, this system places a heavy burden on the system administrator, as it is necessary to prepare in advance incorrect answer data corresponding to the expected incorrect answers for each question text, and is not efficient.

Therefore, one aspect of the present invention aims to provide an English text correction device that can efficiently provide feedback on English text created by a user.

An English sentence correction device according to one aspect of the present invention includes an English sentence acquisition unit that acquires an English sentence created by a user as an answer to a question sentence, a first acquisition unit that acquires a first word string consisting of a plurality of first words by breaking down the English sentence into words, a second acquisition unit that acquires a second word string consisting of a plurality of second words that constitute a correct sentence corresponding to the question sentence, an extraction unit that extracts an erroneous word, which is a first word that does not match a second word, by comparing the first word string and the second word string in order from the first word, an estimation unit that estimates the reason for the error in the English sentence by comparing first part-of-speech information related to the part of speech of the erroneous word with second part-of-speech information related to the part of speech of the second word corresponding to the erroneous word, and a presentation unit that presents the reason for the error estimated by the estimation unit to a user.

In an English correction device according to one aspect of the present invention, an incorrect word is extracted by comparing a first word string constituting an English sentence created by a user with a second word string constituting a correct sentence. Then, a reason for the error is inferred based on a comparison result between first part-of-speech information on the part of speech of the incorrect word and second part-of-speech information on the part of speech of a second word corresponding to the incorrect word, and the reason for the error is fed back to the user. With this mechanism, the reason for the error can be automatically inferred by a predetermined processing procedure, and there is no need to prepare in advance incorrect answer data that associates an expected incorrect answer (English sentence) for the question sentence with an explanation corresponding to the incorrect answer. Therefore, with the English correction device, feedback on the English sentence created by the user can be efficiently provided.

According to one aspect of the present invention, an English text correction device can be provided that can efficiently provide feedback on English text created by a user.

1 is a diagram showing a functional configuration of an English text correction device according to an embodiment; FIG. 13 is a diagram showing an example of a feedback function of an English text correction device. 10 is a flowchart showing an example of the operation of the English text correction device. FIG. 11 is a diagram illustrating a first example of a first estimation process. FIG. 11 is a diagram illustrating a second example of the first estimation process. FIG. 11 is a diagram illustrating a first example of a second estimation process. FIG. 11 is a diagram illustrating a second example of the second estimation process. FIG. 11 is a diagram illustrating a first example of a third estimation process. FIG. 13 is a diagram illustrating a second example of the third estimation process. FIG. 13 is a diagram illustrating a first example of a fourth estimation process. FIG. 1 is a diagram illustrating an example of a hardware configuration of an English text correction device.

Hereinafter, one embodiment of the present invention will be described in detail with reference to the attached drawings. In the description of the drawings, the same or corresponding elements are given the same reference numerals, and duplicate explanations will be omitted.

Figure 1 is a diagram showing the functional configuration of an English correction device 10 according to one embodiment. The English correction device 10 has a function of acquiring an English sentence (English composition) created by a user in response to a certain question sentence, estimating the reason for the error if the English sentence is an incorrect answer, and feeding back the estimated reason for the error to the user. Here, the reason for the error is information indicating what part of the user's English sentence contains what kind of error.

Figure 2 is a diagram showing an example of a feedback function by the English correction device 10. Figure 2 shows an example of a screen SC of an English correction service provided to a user on a browser or application, for example. Initially, part P1 is displayed on the screen SC. Part P1 includes a question sentence and an answer window W. Here, as an example, part P1 presents the text "I want some water" written in Japanese as the question sentence. The answer window W is a part that accepts input of an answer to the question sentence by the user (here, an English translation corresponding to the question sentence). Here, as an example, the English sentence "I want some water." is input by the user in the answer window W. When the user completes input of the English sentence and presses the "Answer" button in the answer window W, the English sentence input by the user is sent to the English correction device 10. If the English sentence is an incorrect answer and the English sentence correction device 10 is able to estimate the reason for the error, it presents feedback information FB including the reason for the error to the user.

In the example of FIG. 2, the English correction device 10 displays a portion P2 showing the correction result including the feedback information FB and the model answer (i.e., the correct sentence corresponding to the question sentence) on the screen SC. In this example, the feedback information FB is text that informs the user of the reason for the error in the English sentence created by the user. In this example, since the conjugation of "wants" in the English sentence created by the user is incorrect, as an example, the text "The verb conjugation is incorrect. Change "wants" to "want"!" is displayed as the feedback information FB. This mechanism allows the user to properly understand the reason for the error, thereby improving the effectiveness of the user's self-study. Note that in the example of FIG. 2, the feedback information FB expressed as text is presented to the user, but feedback information expressed in a form other than text, such as audio, may also be presented to the user.

The English correction device 10 is composed of one or more computer devices. The form of the English correction device 10 is not limited to a specific form. For example, the English correction device 10 may be a terminal such as a smartphone, tablet terminal, or personal computer owned by a user, or may be a server device configured to be able to communicate with a terminal (client terminal) as described above and configured to process requests from the terminal. Alternatively, the English correction device 10 may be configured as a computer system including a client terminal and a server device.

As shown in FIG. 1, the English text correction device 10 comprises a question DB 10a, a question presentation unit 11, an English text acquisition unit 12, a first acquisition unit 13, a second acquisition unit 14, an extraction unit 15, an estimation unit 16, and a presentation unit 17.

Question DB10a is a database that stores one or more pieces of question data. Each piece of question data includes a question sentence (in the example of FIG. 2, the text "I want some water" written in Japanese) and a correct answer sentence corresponding to the question sentence (in the example of FIG. 2, the text "I want some water" written in English).

The question presentation unit 11 presents to the user a question text of any question data stored in the question DB 10a. For example, the question presentation unit 11 may present to the user a question text of question data specified by the user, or may present to the user a question text of question data randomly extracted from a plurality of question data stored in the question DB 10a.

The English text acquisition unit 12 acquires an English text created by the user as an answer to the question text presented to the user by the question presentation unit 11. Hereinafter, the question text presented to the user by the question presentation unit 11 will be simply referred to as the "question text." In the example of FIG. 2, the English text acquisition unit 12 acquires an English text entered into the answer window W by the user.

The first acquisition unit 13 acquires a first word string consisting of a plurality of first words by breaking down the English sentence acquired by the English sentence acquisition unit 12 into words. In the present embodiment, as an example, the first acquisition unit 13 acquires the first word string by performing morphological analysis on the English sentence, and estimates part-of-speech information on each of the plurality of first words. The part-of-speech information includes information indicating the category of the part of speech, such as verb, adjective, adverb, noun, auxiliary verb, etc., and also includes incidental information on the part of speech. For example, when the category of the part of speech is verb, the part-of-speech information includes information on tense and conjugation, etc., as incidental information on the part of speech. In other words, for a first word that is a verb, for example, the first acquisition unit 13 estimates the part of speech category "verb", as well as incidental information such as tense (information on infinitive, present tense, past tense, etc.) and conjugation (information on third person singular, information other than third person singular, etc.). Note that a conventionally known method can be used as such a morphological analysis method.

For example, as in the example of Figure 2, when the English sentence input by the user is "I want some water.", the first acquisition unit 13 acquires a first word string {"I", "want", "some", "water", "."} consisting of multiple (here, five including a period) first words "I", "want", "some", "water", and ".". Note that the comma (period) may be excluded from the first word string. The first acquisition unit 13 also acquires (estimates) part-of-speech information of each first word. In the above example, the first acquisition unit 13 acquires "PP (personal pronoun)" as the part of speech information of the first word "I", "VBZ (Verb (third person singular present tense))" as the part of speech information of the first word "wants", "DT (determinative)" as the part of speech information of the first word "some", "NN (Noun (singular))" as the part of speech information of the first word "water", and ". (period)" as the part of speech information of the first word ".". Note that notations such as PP included in the part of speech information in this embodiment are part of speech tags commonly used for English documents.

The second acquisition unit 14 acquires a second word string consisting of a plurality of second words that constitute a correct sentence corresponding to the question sentence. In this embodiment, the second acquisition unit 14 acquires the correct sentence by referring to the question DB 10a. Then, the second acquisition unit 14 acquires the second word string by performing a morphological analysis of the correct sentence, and estimates part-of-speech information for each of the plurality of second words. The morphological analysis performed by the second acquisition unit 14 is similar to the morphological analysis performed by the first acquisition unit 13 described above.

For example, as in the example of Figure 2, when the correct sentence is "I want some water.", the second acquisition unit 14 acquires a second word string {"I", "want", "some", "water", "."} consisting of multiple (here, five including a period) second words "I", "want", "some", "water", and ".". Note that the comma (period) may be excluded from the second word string. In addition, the second acquisition unit 14 acquires (estimates) part-of-speech information of each second word. In the above example, the second acquisition unit 14 acquires "PP (personal pronoun)" as the part of speech information of the second word "I", acquires "VBP (Verb (present tense other than third person singular))" as the part of speech information of the second word "want", acquires "DT (determinative)" as the part of speech information of the second word "some", acquires "NN (Noun (singular)" as the part of speech information of the second word "water", and acquires ". (period)" as the part of speech information of the second word ".".

In addition, the second word string constituting the correct sentence and the part-of-speech information of each second word may be stored in question DB 10a in advance. For example, when question data is registered in question DB 10a (or at any time after registration), a process may be executed to acquire (estimate) the part-of-speech information of the second word string and each second word by morphologically analyzing the correct sentence of the question data. In this case, the second acquisition unit 14 can acquire the part-of-speech information of the second word string and each second word constituting the correct sentence corresponding to the question sentence by referring to question DB 10a.

The extraction unit 15 compares the first word string acquired by the first acquisition unit 13 with the second word string acquired by the second acquisition unit 14, starting from the first word, to extract erroneous words that are first words that do not match the second words. In the above example, the second first word "wants" in the first word string and the second second word "want" in the second word string do not match each other, so the first word "wants" is extracted as an erroneous word. In addition, "want" is extracted as the second word corresponding to the first word "wants".

The estimation unit 16 estimates the reason for the error in the English sentence by comparing the first part-of-speech information on the part of speech of the erroneous word extracted by the extraction unit 15 (here, the part-of-speech information "VBZ (Verb (third person singular present tense)" of the second first word "wants" in the first word string) with the second part-of-speech information on the second word corresponding to the erroneous word (here, the part-of-speech information "VBP (Verb (present tense other than third person singular)" of the second second word "want" in the second word string). In this embodiment, the estimation unit 16 acquires the part-of-speech information on the erroneous word estimated by the first acquisition unit 13 as the first part-of-speech information. The estimation unit 16 also acquires the part-of-speech information on the second word corresponding to the erroneous word estimated by the second acquisition unit 14 as the second part-of-speech information. Details of the processing by the estimation unit 16 will be described later.

The presentation unit 17 presents to the user the reason for the error estimated by the estimation unit 16. As described above, in this embodiment, the presentation unit 17 displays feedback information FB including the reason for the error expressed in text on the screen SC.

An example of the processing of the English correction device 10 will be described with reference to the flowchart shown in Figure 3.

In step S1, the question presentation unit 11 presents to the user a question statement of any question data stored in the question DB 10a.

In step S2, the English sentence acquisition unit 12 acquires an English sentence created by the user as an answer to the question sentence.

In step S3, the first acquisition unit 13 acquires a first word string consisting of a plurality of first words that constitute the English sentence, and acquires (estimates) part-of-speech information for each first word.

In step S4, the second acquisition unit 14 acquires a second word string consisting of a plurality of second words that constitute the correct sentence corresponding to the question sentence, and acquires (estimates) part-of-speech information for each second word.

In step S5, the extraction unit 15 compares the first word string and the second word string starting from the first word to extract erroneous words, which are first words that do not match the second word.

In steps S6 to S12, the estimation unit 16 estimates the reason for the error of the erroneous word. In the present embodiment, as an example, the estimation unit 16 first determines whether or not the part-of-speech information of the erroneous word (first part-of-speech information) has been acquired (step S6). If the first part-of-speech information has not been acquired (step S6: NO), the estimation unit 16 performs a spelling check of the erroneous word, and if a spelling mistake of the erroneous word is detected by the spelling check, it estimates that the spelling mistake is the reason for the error (step S7). For example, there may be a spelling mistake in the erroneous word, and the erroneous word may be a word that does not exist in the dictionary, such as "wnat" (a misspelling of "want"). In such a case, in step S3, the first acquisition unit 13 cannot appropriately estimate the part-of-speech information of the first word. Therefore, as described above, by performing a spelling check when the first part-of-speech information has not been acquired, the reason for the error (spelling mistake) can be appropriately identified.

On the other hand, if the first part-of-speech information has been acquired (step S6: YES), the estimation unit 16 performs estimation processing according to the part-of-speech category of the erroneous word (steps S8 to S12). Below, the processing of the estimation unit 16 in each case is described with specific examples.

[First Estimation Process]
When the part of speech category of the erroneous word is a verb (step S8: verb), the estimation unit 16 executes a first estimation process (step S9). Specifically, when the part of speech category indicated by the first part of speech information (i.e., the part of speech category of the erroneous word) and the part of speech category indicated by the second part of speech information (i.e., the part of speech category of the second word corresponding to the erroneous word) are both verbs, and the original form of the verb of the erroneous word matches the original form of the verb of the second word corresponding to the erroneous word, the estimation unit 16 estimates that the reason for the error is an error in verb conjugation or an error in verb tense based on the comparison result between the first part of speech information and the second part of speech information (i.e., the difference between the first part of speech information and the second part of speech information).

(First Example of First Estimation Process)
Fig. 4 is a diagram showing a first example (same as the example in Fig. 2) of the first estimation process. In the example in Fig. 4, in step S5, the extraction unit 15 obtains error information [2, [wants, want]] by comparing the first word string {"I", "want", "some", "water", "."} with the second word string {"I", "want", "some", "water", "."}. Here, the first element "2" of the error information is information indicating the position of the erroneous word from the beginning. Also, the second element [wants, want] of the error information is information indicating an erroneous word on the left side and a second word corresponding to the erroneous word on the right side. In this example, the part-of-speech category indicated by the first part-of-speech information "VBZ(Verb (third person singular present tense)" and the part-of-speech category indicated by the second part-of-speech information "VBP(Verb (present tense other than third person singular)" are both verbs. Furthermore, the original form of the verb of the erroneous word "wants" and the original form of the verb of the second word "want" corresponding to the erroneous word are both "want," which matches each other.

Therefore, the estimation unit 16 estimates that the reason for the error is an error in verb conjugation or an error in verb tense based on the comparison result between the first part of speech information and the second part of speech information. In this example, the difference between the first part of speech information and the second part of speech information is that one is "third person singular" while the other is "other than third person singular" (i.e., a difference in verb conjugation). Therefore, the estimation unit 16 estimates that the reason for the error is an error in verb conjugation based on this difference. The estimation unit 16 can identify the reason for the error corresponding to the difference between the first part of speech information and the second part of speech information, for example, by referring to table information or the like in which error reasons corresponding to differences between parts of speech information are stored in advance.

(Second Example of First Estimation Process)
Fig. 5 is a diagram showing a second example of the first estimation process. In the example of Fig. 5, the user inputs the English sentence "My parents give me a watch for my birthday" in response to the question "My parents gave me a watch for my birthday." Here, the correct answer sentence corresponding to the question is "My parents gave me a watch for my birthday." In this case, in step S5, the extraction unit 15 acquires error information [3, [give, give]] by comparing the first word string {"My", "parents", "give", "me", "a", "watch", "for", "my", "birthday", "."} with the second word string {"My", "parents", "give", "me", "a", "watch", "for", "my", "birthday", "."}. In this example, the part of speech category indicated by the first part of speech information "VB (verb (infinitive))" and the part of speech category indicated by the second part of speech information "VBD (verb (past tense))" are both verbs. In addition, the original form of the verb of the erroneous word "give" and the original form of the verb of the second word "gave" corresponding to the erroneous word are both "give", which coincide with each other.

Therefore, the estimation unit 16 estimates that the reason for the error is an error in verb conjugation or an error in verb tense based on the comparison result between the first part of speech information and the second part of speech information. In this example, the difference between the first part of speech information and the second part of speech information is that one is the "original form" while the other is the "past tense" (i.e., the difference in tense). Therefore, the estimation unit 16 estimates that the reason for the error is an error in tense based on this difference.

[Second Estimation Process]
When the part-of-speech category of the erroneous word is a preposition (step S8: preposition), the estimation unit 16 executes a second estimation process (step S10).

(First Example of Second Estimation Process)
When the part-of-speech category indicated by the first part-of-speech information matches the part-of-speech category indicated by the second part-of-speech information and the matching category is a preposition, the estimation unit 16 estimates that the error reason is an error in the preposition.

Figure 6 is a diagram showing a first example of the second estimation process. In the example of Figure 6, the user inputs the English sentence "The restaurant should be closed in night." in response to the question sentence "The restaurant should be closed at night." Here, the correct sentence corresponding to the above question sentence is "The restaurant should be closed at night." In this case, in step S5, the extraction unit 15 obtains error information [6, [in, at]] by comparing the first word string {"The", "restaurant", "should", "be", "closed", "in", "night", "."} with the second word string {"The", "restaurant", "should", "be", "closed", "at", "night", "."}. In this example, the part of speech category indicated by the first part of speech information "IN (preposition)" and the part of speech category indicated by the second part of speech information "IN (preposition)" are both prepositions and match each other. Therefore, in this case, the estimation unit 16 estimates that the error is due to an error in a preposition.

(Second Example of Second Estimation Process)
If the word string obtained by excluding the erroneous word from the first word string matches the second word string, and the part-of-speech category indicated by the first part-of-speech information is a preposition, the estimation unit 16 estimates that the reason for the error is that the erroneous word is an unnecessary preposition.

Figure 7 is a diagram showing a second example of the second estimation process. In the example of Figure 7, the user inputs the English sentence "Do you want to visit famous temples?" in response to the question "Do you want to visit famous temples?". Here, the correct answer sentence corresponding to the above question is "Do you want to visit famous temples?" In this case, in step S5, the extraction unit 15 obtains the error information [6, [to, famous]] by comparing the first word string {"Do", "you", "want", "to", "visit", "to", "famous", "templates", "?"} with the second word string {"Do", "you", "want", "to", "visit", "famous", "templates", "?"}. In this example, the word string obtained by excluding the erroneous word "to" from the first word string matches the second word string. In addition, the category of the part of speech indicated by the first part of speech information "TO (preposition)" is a preposition. Therefore, in this case, the estimation unit 16 estimates that the reason for the error is that the erroneous word is an unnecessary preposition.

[Third Estimation Process]
When the part-of-speech category of the erroneous word is an auxiliary verb (step S8: auxiliary verb), the estimation unit 16 executes a third estimation process (step S11).

(First Example of Third Estimation Process)
When the part-of-speech category indicated by the first part-of-speech information matches the part-of-speech category indicated by the second part-of-speech information and the matching category is an auxiliary verb, the estimation unit 16 estimates that the error reason is an error in the auxiliary verb.

Figure 8 is a diagram showing a first example of the third estimation process. In the example of Figure 8, the user inputs the English sentence "The picture could be seen in the museum" in response to the question sentence "The picture can be seen in the museum." Here, the correct sentence corresponding to the above question sentence is "The picture can be seen in the museum." In this case, in step S5, the extraction unit 15 compares the first word string {"The", "picture", "could", "be", "seen", "in", "the", "museum", "."} with the second word string {"The", "picture", "can", "be", "seen", "in", "the", "museum", "."} to obtain error information [3, [could, can]]. In this example, the part of speech category indicated by the first part of speech information "MD (auxiliary verb)" and the part of speech category indicated by the second part of speech information "MD (auxiliary verb)" are both auxiliary verbs, and are consistent with each other. Therefore, in this case, the estimation unit 16 estimates that the error is due to an error in the auxiliary verb.

(Second Example of Third Estimation Process)
If the word string obtained by excluding the erroneous word from the first word string matches the second word string and the part of speech category indicated by the first part of speech information is an auxiliary verb, the estimation unit 16 estimates that the reason for the error is that the erroneous word is an unnecessary auxiliary verb.

Figure 9 is a diagram showing a second example of the third estimation process. In the example of Figure 9, the user inputs the English sentence "I can want to speak English" in response to the question sentence "I want to speak English." Here, the correct answer sentence corresponding to the above question sentence is "I want to speak English." In this case, in step S5, the extraction unit 15 obtains error information [2, [can, want]] by comparing the first word string {"I", "can", "want", "to", "speak", "English", "."} with the second word string {"I", "want", "to", "speak", "English", "."}. In this example, the word string obtained by excluding the erroneous word "can" from the first word string matches the second word string. The part of speech category indicated by the first part of speech information "MD (auxiliary verb)" is an auxiliary verb. Therefore, in this case, the estimation unit 16 estimates that the reason for the error is that the erroneous word is an unnecessary auxiliary verb.

[Fourth Estimation Process]
When the category of the part of speech of the erroneous word is neither a verb, a preposition nor an auxiliary verb (step S8: other), the estimation unit 16 executes a fourth estimation process (step S12).

(First Example of Fourth Estimation Process)
When the part-of-speech category indicated by the first part-of-speech information does not match the part-of-speech category indicated by the second part-of-speech information, the estimation unit 16 searches for a first word located after the erroneous word in the first word string and a second word located after the second word corresponding to the erroneous word in the second word string. Then, when the first word and the second word, which are verbs whose original forms match each other, are acquired by the search, the estimation unit 16 estimates the reason for the error based on a comparison result between the part-of-speech information of the first word and the part-of-speech information of the second word.

Figure 10 is a diagram showing a first example of the fourth estimation process. In the example of Figure 10, the user inputs the English sentence "The movie just started" in response to the question sentence "The movie has just started." Here, the correct answer sentence corresponding to the above question sentence is "The movie has just started." In this case, in step S5, the extraction unit 15 obtains error information [3, [just, has]] by comparing the first word string {"The", "movie", "just", "started", "."} with the second word string {"The", "movie", "has", "just", "started", "."}. In this example, the part-of-speech category "adverb" indicated by the first part-of-speech information "RB (adverb)" does not match the part-of-speech category "verb" indicated by the second part-of-speech information "VBZ (verb (third person singular present tense))". Therefore, the estimation unit 16 searches for a first word located after the erroneous word in the first word string and a second word located after the second word corresponding to the erroneous word in the second word string. In this example, the first word "started", which is the first word after the erroneous word, and the second word "started", which is the second word after the second word corresponding to the erroneous word, are verbs whose root forms "start" match each other. Therefore, the first word "started" and the second word "started" are acquired by the above search. Then, the estimation unit 16 compares the part of speech information of the first word "started", "VBD (verb (past tense))", with the part of speech information of the second word "started", "VBN (verb (past participle))". As a result of this comparison, the difference between the part of speech information of the first word and the part of speech information of the second word is that one is "past tense" while the other is "past participle" (i.e., a difference in tense). Therefore, based on this difference, the estimation unit 16 estimates that the reason for the error is an error in tense.

(Second Example of Fourth Estimation Process)
If the word string obtained by excluding the second word corresponding to the erroneous word from the second word string matches the first word string, and the part-of-speech category indicated by the second part-of-speech information is a preposition or an auxiliary verb, the estimation unit 16 estimates that the reason for the error is a lack of a preposition or an auxiliary verb.

For example, consider the case where the English sentence created by the user for the question "I walk to the station" is "I walk the station.", while the correct answer is "I walk to the station." In this case, in step S3, the first word string {"I", "walk", "the", "station", "."} is obtained, and in step S4, the second word string {"I", "walk", "to", "the", "station", "."} is obtained. As a result, in step S5, the third first word "the" in the first word string is extracted as the incorrect word, and the third second word "to" in the second word string is extracted as the second word corresponding to the incorrect word. In this case, the word string obtained by excluding the second word "to" corresponding to the incorrect word from the second word string matches the first word string. Furthermore, the category of the part of speech indicated by the second part of speech information (the part of speech information of "to" "TO (preposition)") is a preposition. Therefore, in this case, the estimation unit 16 estimates that the reason for the error is a lack of a preposition.

Also, consider the case where the English sentence created by the user for the question sentence "I can play the piano" is "I play the piano.", while the correct answer sentence is "I can play the piano." In this case, in step S3, the first word string {"I", "play", "the", "piano", "."} is obtained, and in step S4, the second word string {"I", "can", "play", "the", "piano", "."} is obtained. As a result, in step S5, the second first word "play" in the first word string is extracted as an incorrect word, and the second second word "can" in the second word string is extracted as the second word corresponding to the incorrect word. In this case, the word string obtained by excluding the second word "can" corresponding to the incorrect word from the second word string matches the first word string. Furthermore, the category of the part of speech indicated by the second part of speech information (the part of speech information of “can” “MD (auxiliary verb)”) is an auxiliary verb. Therefore, in this case, the estimation unit 16 estimates that the reason for the error is a lack of an auxiliary verb.

Finally, in step S13, the presentation unit 17 presents the reason for the error estimated by the estimation unit 16 to the user.

In the English correction device 10 described above, an incorrect word is extracted by comparing a first word string constituting an English sentence created by a user with a second word string constituting a correct sentence. Then, the reason for the error is estimated based on the result of comparing the first part-of-speech information on the part of speech of the incorrect word with the second part-of-speech information on the part of speech of the second word corresponding to the incorrect word, and the reason for the error is fed back to the user. With this mechanism, the reason for the error can be automatically estimated by a predetermined processing procedure, and there is no need to prepare in advance incorrect answer data that associates an expected incorrect answer (English sentence) for the question sentence with an explanation corresponding to the incorrect answer. Therefore, the English correction device 10 can efficiently provide feedback on the English sentence created by the user.

The first acquisition unit 13 also performs morphological analysis on the English sentence to acquire the first word string and estimate information on the part of speech of each of the multiple first words. The estimation unit 16 then acquires information on the part of speech estimated by the first acquisition unit 13 for the erroneous words as first part of speech information. According to the above configuration, by performing morphological analysis on the English sentence created by the user, it is possible to simultaneously execute the process of acquiring the first word string (i.e., the process of breaking down the English sentence into multiple first words) and the process of acquiring information on the part of speech required to estimate the reason for the error. As a result, the efficiency of the process can be improved.

The second acquisition unit 14 also performs morphological analysis on the correct sentence to acquire a second word string and estimate information on the part of speech of each of the multiple second words. The estimation unit 16 then acquires information on the part of speech estimated by the second acquisition unit 14 for the second word corresponding to the error word as second part of speech information. According to the above configuration, by performing morphological analysis on the correct sentence, it is possible to simultaneously execute the process of acquiring the second word string (i.e., the process of decomposing the correct sentence into multiple second words) and the process of acquiring information on the part of speech required to estimate the reason for the error. As a result, the efficiency of the process can be improved.

The estimation unit 16 is also configured to be able to execute the first example (see FIG. 4) and the second example (see FIG. 5) of the first estimation process described above. With the above configuration, it is possible to provide appropriate feedback to the user on errors in verb conjugation or verb tense.

The estimation unit 16 is also configured to be able to execute the first example of the second estimation process (see FIG. 6) and the first example of the third estimation process (see FIG. 8) described above. With the above configuration, it is possible to provide appropriate feedback to the user about errors in prepositions or auxiliary verbs.

The estimation unit 16 is also configured to be able to execute the second example of the second estimation process (see FIG. 7) and the second example of the third estimation process (see FIG. 9) described above. According to the above configuration, it is possible to provide appropriate feedback to the user that an unnecessary preposition or auxiliary verb is included in an English sentence created by the user.

The estimation unit 16 is also configured to be able to execute the second example of the fourth estimation process described above. With the above configuration, it is possible to provide appropriate feedback to the user that a preposition or auxiliary verb is missing in an English sentence created by the user.

The estimation unit 16 is also configured to be able to execute the first example of the fourth estimation process described above (see FIG. 10). According to the above configuration, when the first word string and the second word string each contain corresponding elements with different numbers of words, such as the past tense of a verb (e.g., "started") and the present perfect tense (e.g., "has started"), it is possible to appropriately estimate the reason for the error based on the word located after the erroneous word (and the second word corresponding to the erroneous word).

Furthermore, when the estimation unit 16 cannot acquire the first part-of-speech information (step S6: NO), it performs a spelling check of the erroneous word, and when a spelling mistake of the erroneous word is detected by the spelling check, it estimates that the spelling mistake is the reason for the error (step S7). According to the above configuration, it is possible to appropriately provide feedback to the user that the English sentence created by the user contains a spelling mistake.

In the above embodiment, the first to fourth estimation processes are exemplified as processes by which the estimation unit 16 estimates the reason for the error. However, the estimation unit 16 may be configured to be able to execute estimation processes other than those described above (for example, processes corresponding to the case where the part of speech of the erroneous word is a "noun"). In addition, the estimation process executed by the estimation unit 16 when the part of speech of the erroneous word is a verb is not limited to the first estimation process described above. That is, the estimation unit 16 may execute estimation processes other than the first estimation process described above when the part of speech of the erroneous word is a verb. The same applies to the case where the part of speech of the erroneous word is a preposition or an auxiliary verb. In addition, the estimation unit 16 does not necessarily have to be configured to be able to execute all of the first to fourth estimation processes described above, and may be configured to execute a part of the first to fourth estimation processes described above. Even in such a case, it is possible to estimate the reason for the error and provide feedback to the user within the scope of what the estimation unit 16 can execute.

Note that the block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or may be realized using two or more devices that are physically or logically separated and directly or indirectly connected (e.g., using wires, wirelessly, etc.) and these multiple devices. The functional blocks may be realized by combining the one device or the multiple devices with software.

Functions include, but are not limited to, judging, determining, assessing, calculating, processing, deriving, investigating, searching, verifying, receiving, sending, outputting, accessing, resolving, selecting, choosing, establishing, comparing, anticipating, expecting, regarding, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping and assigning.

For example, the English correction device 10 in one embodiment of the present disclosure may function as a computer that performs the communication control method of the present disclosure. FIG. 11 is a diagram showing an example of the hardware configuration of the English correction device 10 in one embodiment of the present disclosure. The above-mentioned English correction device 10 may be physically configured as a computer device including a processor 1001, memory 1002, storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, etc.

In the following description, the term "apparatus" may be interpreted as a circuit, device, unit, etc. The hardware configuration of the English text correction device 10 may be configured to include one or more of the devices shown in FIG. 1, or may be configured to exclude some of the devices.

Each function of the English correction device 10 is realized by loading a specific software (program) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of the reading and writing of data in the memory 1002 and storage 1003.

The processor 1001, for example, operates an operating system to control the entire computer. The processor 1001 may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc.

The processor 1001 also reads out programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002, and executes various processes according to these. As the program, a program that causes a computer to execute at least a part of the operations described in the above-mentioned embodiment is used. For example, the estimation unit 16 may be realized by a control program stored in the memory 1002 and operating in the processor 1001, and may be similarly realized for other functional blocks. Although the above-mentioned various processes have been described as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The program may be transmitted from a network via a telecommunications line.

The memory 1002 is a computer-readable recording medium, and may be composed of at least one of, for example, a Read Only Memory (ROM), an Erasable Programmable ROM (EPROM), an Electrically Erasable Programmable ROM (EEPROM), a Random Access Memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing a communication control method according to one embodiment of the present disclosure.

Storage 1003 is a computer-readable recording medium, and may be, for example, at least one of an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other suitable medium including at least one of memory 1002 and storage 1003.

The communication device 1004 is hardware (transmitting/receiving device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, a communication module, etc.

The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that accepts input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that performs output to the outside. Note that the input device 1005 and the output device 1006 may be integrated into one configuration (e.g., a touch panel).

In addition, each device such as the processor 1001 and the memory 1002 is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

In addition, the English correction device 10 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

Although the present embodiment has been described in detail above, it is clear to those skilled in the art that the present embodiment is not limited to the embodiment described in this specification. The present embodiment can be implemented in modified and altered forms without departing from the spirit and scope of the present invention as defined by the claims. Therefore, the description in this specification is intended as an illustrative example and does not have any restrictive meaning with respect to the present embodiment.

The processing steps, sequences, flow charts, etc. of each aspect/embodiment described in this disclosure may be reordered unless inconsistent. For example, the methods described in this disclosure present elements of various steps using an example order and are not limited to the particular order presented.

The input and output information, etc. may be stored in a specific location (e.g., memory) or may be managed using a management table. The input and output information, etc. may be overwritten, updated, or added to. The output information, etc. may be deleted. The input information, etc. may be transmitted to another device.

The determination may be based on a value represented by a single bit (0 or 1), a Boolean (true or false) value, or a numerical comparison (e.g., with a predetermined value).

Each aspect/embodiment described in this disclosure may be used alone, in combination, or switched depending on the execution. In addition, notification of specific information (e.g., notification that "X is the case") is not limited to being done explicitly, but may be done implicitly (e.g., not notifying the specific information).

Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

Additionally, software, instructions, information, etc. may be transmitted and received via a transmission medium. For example, if the software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and/or wireless technologies (such as infrared, microwave), then these wired and/or wireless technologies are included within the definition of a transmission medium.

The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

In addition, the information, parameters, etc. described in this disclosure may be expressed using absolute values, may be expressed using relative values from a predetermined value, or may be expressed using other corresponding information.

The names used for the parameters described above are not intended to be limiting in any respect. Moreover, the formulas etc. using these parameters may differ from those expressly disclosed in this disclosure. The various information elements may be identified by any suitable names, and the various names assigned to these various information elements are not intended to be limiting in any respect.

As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

Any reference to elements using designations such as "first," "second," etc., used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must precede the second element in some way.

When used in this disclosure, the terms "include," "including," and variations thereof are intended to be inclusive, similar to the term "comprising." Additionally, the term "or," as used in this disclosure, is not intended to be an exclusive or.

In this disclosure, where articles have been added by translation, such as a, an, and the in English, this disclosure may include that the nouns following these articles are in the plural form.

In this disclosure, the term "A and B are different" may mean "A and B are different from each other." In addition, the term may mean "A and B are each different from C." Terms such as "separate" and "combined" may also be interpreted in the same way as "different."

10...English text correction device, 10a...question DB, 11...question presentation unit, 12...English text acquisition unit, 13...first acquisition unit, 14...second acquisition unit, 15...extraction unit, 16...estimation unit, 17...presentation unit.

Claims (8)

an English sentence acquisition unit that acquires an English sentence created by a user as an answer to a question;
a first acquisition unit that acquires a first word string consisting of a plurality of first words by breaking down the English sentence into words;
a second acquisition unit that acquires a second word string including a plurality of second words that constitute a correct answer sentence corresponding to the question sentence;
an extraction unit that compares the first word string with the second word string in order from the first word to extract an erroneous word that is the first word that does not match the second word;
an estimation unit that estimates a reason for the error in the English sentence by comparing first part-of-speech information on a part-of-speech of the erroneous word with second part-of-speech information on a part-of-speech of the second word corresponding to the erroneous word;
a presentation unit that presents the error reason estimated by the estimation unit to the user;
Equipped with
The estimation unit, when the word string obtained by excluding the erroneous word from the first word string matches the second word string and the part of speech category indicated by the first part of speech information is a preposition or an auxiliary verb, estimates that the reason for the error is that the erroneous word is an unnecessary preposition or auxiliary verb . an English sentence acquisition unit that acquires an English sentence created by a user as an answer to a question;
a first acquisition unit that acquires a first word string consisting of a plurality of first words by breaking down the English sentence into words;
a second acquisition unit that acquires a second word string including a plurality of second words that constitute a correct answer sentence corresponding to the question sentence;
an extraction unit that compares the first word string with the second word string in order from the first word to extract an erroneous word that is the first word that does not match the second word;
an estimation unit that estimates a reason for the error in the English sentence by comparing first part-of-speech information on a part-of-speech of the erroneous word with second part-of-speech information on a part-of-speech of the second word corresponding to the erroneous word;
a presentation unit that presents the error reason estimated by the estimation unit to the user;
Equipped with
The estimation unit estimates that the reason for the error is a lack of a preposition or an auxiliary verb when a word string obtained by excluding the second word corresponding to the erroneous word from the second word string matches the first word string and the part of speech category indicated by the second part of speech information is a preposition or an auxiliary verb. an English sentence acquisition unit that acquires an English sentence created by a user as an answer to a question;
a first acquisition unit that acquires a first word string consisting of a plurality of first words by breaking down the English sentence into words;
a second acquisition unit that acquires a second word string including a plurality of second words that constitute a correct answer sentence corresponding to the question sentence;
an extraction unit that compares the first word string with the second word string in order from the first word to extract an erroneous word that is the first word that does not match the second word;
an estimation unit that estimates a reason for the error in the English sentence by comparing first part-of-speech information on a part-of-speech of the erroneous word with second part-of-speech information on a part-of-speech of the second word corresponding to the erroneous word;
a presentation unit that presents the error reason estimated by the estimation unit to the user;
Equipped with
The estimation unit is
when the category of the part of speech indicated by the first part of speech information does not match the category of the part of speech indicated by the second part of speech information, searching for the first word located behind the erroneous word in the first word string and the second word located behind the second word corresponding to the erroneous word in the second word string;
When the first word and the second word, which are verbs whose infinitives match each other, are obtained by a search, the English sentence correction device estimates the reason for the error based on the results of comparing part-of-speech information of the first word with part-of-speech information of the second word. the first acquisition unit acquires the first word string by performing a morphological analysis of the English sentence, and estimates information regarding a part of speech of each of the plurality of first words;
The English text correction device according to claim 1 , wherein the estimation unit acquires, as the first part-of-speech information, information on the part of speech estimated for the erroneous word by the first acquisition unit. the second acquisition unit acquires the second word string by performing a morphological analysis of the correct sentence, and estimates information regarding a part of speech of each of the plurality of second words;
The English text correction device according to claim 1 , wherein the estimation unit acquires, as the second part-of-speech information, information on the part of speech estimated by the second acquisition unit for the second word corresponding to the erroneous word. The English text correction device of any one of claims 1 to 5, wherein when the part-of-speech category indicated by the first part-of-speech information and the part-of-speech category indicated by the second part-of-speech information are both verbs and the infinitive form of the verb of the erroneous word matches the infinitive form of the verb of the second word corresponding to the erroneous word, the estimation unit estimates that the reason for the error is an error in verb conjugation or an error in verb tense based on a comparison result between the first part-of-speech information and the second part-of - speech information. The English text correction device according to any one of claims 1 to 6, wherein the estimation unit estimates that the reason for the error is an error in a preposition or an auxiliary verb when a part-of-speech category indicated by the first part-of-speech information matches a part-of-speech category indicated by the second part-of-speech information and the matching category is a preposition or an auxiliary verb. The English text correction device according to any one of claims 1 to 7, wherein the estimation unit performs a spelling check of the erroneous word when the first part-of-speech information cannot be acquired, and when a spelling mistake of the erroneous word is detected by the spelling check, estimates that the spelling mistake is the reason for the error .

Images