JPH063596B2 - Japanese sentence proofreading device - Google Patents

Description

TECHNICAL FIELD The present invention relates to a Japanese sentence proofreading device for extracting and proofreading notations and expressions that do not meet specific criteria from Japanese sentences.

<Conventional Technology> In Europe and the United States, word processors have developed from an early stage, and related technologies have advanced, and devices having spell checking and collecting functions have been put into practical use. Compared to Western words that are written in units of words, Japanese is usually written in Kanji and Kana interchange without punctuation, and the orthography is not thorough. However, a device for automating calibration has not been put into practical use.

Conventionally used as a proofreading method for Japanese, multiple people make a pair and read together to extract problematic points, or a person with specialized knowledge of proofreading writes sentences based on the knowledge. This is a method of sequentially collating.

For the former, there has been proposed a proofreading device capable of analyzing a sentence in which kanji and kana are mixed, converting it into a voice, and performing reading together with a machine.

However, the device for the latter requires a function of supporting the automation of the calibration or the specialization of the calibration, and requires a higher level of technology. No specific means have been reported.

<Problems to be solved by the invention> In order to perform calibration, specialized knowledge of calibration is required.
It took time to learn it.

In addition, the number of people who have specialized knowledge of proofreading is small, and there is a problem when proofreading a large amount of sentences or when urgent proofreading is required.

Also, from the standpoint of an expert who has the knowledge of calibration, it is necessary to pay attention to the fine details in order to perform calibration correctly.
I had a mental burden.

Nevertheless, there were some errors that were difficult for humans to find and errors that were easily overlooked, and there was a problem in terms of calibration accuracy.

Also, when an ordinary person who does not have specialized knowledge of proofreading uses a word processor or the like to create a document, it requires reprocessing such as reading, printing, and copying of the document file for proofreading of small errors. There was a problem in the efficiency of document creation work.

There is no specific proposal other than the Japanese grammar proofreading system by voice reading, but spell checking in Europe and America,
The method of implementing the collect function has a problem that it is difficult to grasp the relationship between the original sentence and the sentence to be proofread, which is displayed in a different place from the sentence to be investigated.

The present invention extracts a character / symbol string to be proofread from a Japanese sentence (hereinafter, the character / symbol string may be referred to as a character string without special notice) and replaces it with the character string. The present invention aims to solve such a problem by presenting a column as a candidate in the same sentence as the original sentence and providing a means for allowing the user of the apparatus to select the correct notation from the candidates.

<Means for Solving Problems> The present invention does not meet the criteria of a dictionary means that stores a headline and grammatical information of the headline, a grammar means that stores a connection relation of the headline or grammatical information of the dictionary means. A proofreading dictionary means for storing the notation and a correct notation corresponding to the notation, a storage means for storing the sentence, and a dividing means for dividing the sentence stored in the storage means into temporary clauses,
First deciding means for deciding whether or not the temporary bunsetsu is a normal bunsetsu by referring to the dictionary means and the grammar means for each temporary bunsetsu divided by the dividing means; In response to the judgment by the judgment means 1 that the temporary clause is not a normal clause, the temporary clause is referred to the proofreading dictionary means and the grammar means, and the temporary clause is proofread by the proofreading dictionary. In response to the second judgment means for judging whether or not it is a normal phrase, and the judgment of the normal phrase by the second judgment means, the temporary phrase and the temporary dictionary of the proofreading dictionary means are provisional. Display means for displaying the correct notation of bunsetsu,
It comprises a selection means for selecting a desired notation from the candidates displayed by the display means.

<Operation> The present invention divides a sentence into temporary clauses, judges whether or not the temporary clauses are normal by referring to the dictionary means and the grammar means for the divided temporary clauses, and determines whether the temporary clauses are normal. Is not normal, that is, when it is determined that proofreading is necessary, the proofreading dictionary means and grammar means are referred to for the provisional bunsetsu,
When it is determined that the provisional bunsetsu becomes a normal bunsetsu by proofreading of the proofreading dictionary, a candidate of correct notation of the provisional bunsetsu and the tentative bunsetsu of the proofreading dictionary means is displayed to allow the user to select. The text is proofread.

<Example> The present invention will be described in detail with reference to the drawings.

FIG. 1 is a block diagram of a Japanese sentence proofreading device according to the present invention.

In the figure, 1 is a means for inputting a Japanese character string. Reference numeral 2 is a means for storing the Japanese character string input by the input means. Although a keyboard is usually used as the input means, an external storage means for storing the input Japanese character string, such as a floppy disk or a magnetic tape, can be used instead of the sequential input.
That is, there may be a configuration in which 1 is omitted.

Reference numeral 3 is a means for storing a dictionary consisting of Japanese character strings that meet the criteria. 4 is a means for storing Japanese grammar. Since the orthography of Japanese has not been established, it is considered that the notation and grammar that meet certain standards are correct. When the correct notation and grammar are described below, it means that they meet a certain standard.

5 compares and collates the Japanese character strings accumulated in 2 above with the dictionary stored in 3 and the grammar stored in 4 to extract a portion that may be proofread and store the intermediate result. It is a control means for controlling the display and controlling the display. The control means includes means for storing the result obtained by the control.

Reference numeral 6 is a means for storing a proofreading dictionary composed of a character string of correct notation corresponding to the character string extracted by 5. 7 is a CR that displays the input Japanese, the result of collation, the character string to be proofread, the character string to be replaced, etc.
It is a display means such as T. Reference numeral 8 is a means for selecting a correct notation candidate from the candidates to be replaced displayed by 7.

FIG. 2 is an example of a character string input by the input means.

FIG. 3 is an example of the dictionary stored in 3. Reference numeral 9 is a headline to be compared with the input character string. The notation of this heading is based on, for example, the provisions of a modern language pseudonym, a newspaper company, a company, etc. by the National Language Council. In the present case,
"Accept" indicates that "receive" is the correct notation standard. Reference numeral 10 is part-of-speech information which is one of the grammatical information of the headline. Thus, the dictionary may include grammatical information for performing grammatical processing of the headline. 11 indicates that the headline is an independent word, and 12 indicates that it is an adjunct word. The inflectional ending in the adjunct may be a heading connected to the stem of an independent word that has inflection.

FIG. 4 is an example of the grammatical information stored in 4. The heading shown in FIG. 3 is also shown for the sake of clarity. 1
Reference numeral 3 is grammatical information defining the connection relation of the headline or part-of-speech information represented by 10. For example, the stem "reception" of the lower one-stage verb is connected to the auxiliary verb "ru", and the stem "reception" of the five-stage verb is "inflectional ending of la line" or "tsu"
It means that you can connect to.

14 is a grammar that defines whether or not each heading can satisfy the ending condition of the clause, ○ indicates the condition of ending the segment, ×
Indicates that it is not met.

FIG. 5 shows a proofreading dictionary for replacing a notation that does not meet the standard with a correct notation. FIG. 5 shows a proofreading dictionary for replacing a notation that does not meet the standard with a correct notation. 15 is a notation that does not meet the standard, 16
Is the correct notation corresponding to it. It is also possible to substitute 16 for the pointer of the corresponding heading in the dictionary of FIG.

FIG. 6 is a schematic flow chart of the present invention. 17 stores the input character string in the stack in 5. 18 tentatively divides the accumulated character / symbol string by a kanji code or the like. Reference numeral 19 reads each provisionally divided input character string. 20 compares the input character string read in 19 with the dictionary heading. Depending on the result, it branches if the collation succeeds or fails. Reference numeral 21 checks the grammatical constraint conditions for the character string that has been successfully matched. 22 stores a character string that has been successfully matched with both the dictionary and the grammar. 23 checks the next input character string to be collated. If the collation of either the dictionary or the grammar 24 fails, the character string currently collated is regarded as inappropriate and another input character string is cut out. 25 is a proofreading dictionary heading and 24
Compare the character strings cut out with. 26 performs a match of 24 grammatical matches. Reference numeral 27 displays a proofreading dictionary, a character string to be replaced after successful grammar matching, and a portion to be proofread.

No. 28 does not have a character string to be replaced, but it is displayed as a part that is highly likely to be calibrated, distinguishing it from others. Numeral 29 is for selecting a notation to be replaced presented by this device or inputting separately.
Proofread by editing means.

FIG. 7 shows an example of display of a character string to be proofread and a character string to be replaced, which is a feature of this patent.

Reference numeral 30 is a character string of the input original text. Reference numeral 31 is a symbol indicating that the character string sandwiched between them is the replacement character string, and may be anything as long as it can be distinguished from the original sentence. 32 is a character string to be replaced.

The flow of actual processing will be described below using the example sentences shown in FIG. 2 and the dictionaries and grammars shown in FIGS. 3 and 4. First, the input character string “receive a postcard.” Is stacked at 5. Next, the input character string is provisionally divided using the code of the stacked character strings. This will "receive the postcard."
Is divided into "postcard" and "receive." (18).
Next, the divided input character "postcard" is read by the control device 5 (19) and collated (20) with the dictionary heading (9) in FIGS. 3 and 4. In this case, the "postcard" part in the dictionary matches. This information is stacked in 5, and the connection condition (10) of the corresponding heading is compared with the next input character string.
In the present case, both are “w”, and they match.

Next, the clause end condition of the item having the heading "o" in FIG. 3 is checked at 14 in FIG. 4 (21). From 14, it is found that the phrase end condition is satisfied in the present case, and "postcard is" is stacked as a normal phrase in 5 (22).

Next, the process proceeds to the process of "receive" (23).
By comparing "receive" with the dictionary in the same manner as "postcard", the "receive" in the dictionary matches. "received"
Since the “ru” derived from the connection condition 13 of No. does not match the subsequent input character string, it is determined that connection is impossible. Also,
Since "receive" satisfies the clause end condition according to 14 in FIG. 4, "receive" is stacked in 5 as a normal clause.

By repeating the above process, the dictionary is collated with "Tori." This time, the dictionary collation fails and the process branches to 24. Here, the phrase segmentation is reviewed, and the "receive" that was previously stacked as a normal segment is returned to the starting point of dictionary matching.

As a result, "receive." Is subject to dictionary matching.
This time, the heading (15) of the proofreading dictionary is compared with the heading (15) of the dictionary of FIGS. 3 and 4 (25). As a result, the "receiver" matches. By performing grammatical matching in the same manner as "postcard" (26), a branch is made when success or failure occurs. In the present example, the grammatical condition is satisfied, and "receive" is stacked as a proofreading clause (27). At the same time, "receive." For "receive." Can be extracted as a replacement candidate and displayed on 7 as shown in FIG.

When the notation presented as a candidate for the notation to be replaced by the device is correct, a selection means such as a keyboard is used to select the character string "receive" presented by the device to receive the postcard "receive a postcard." Can be calibrated (29).

On the contrary, if the original sentence is correct, the notation of the original sentence can be selected by the original sentence selection key.

I will briefly explain the branch that does not appear in the above explanation. In the case of a branch that fails to check the proofreading dictionary or the grammar, there is no proofreading candidate presented by the apparatus, but it can be proofreading separately by distinguishing from other parts as a part requiring high proofreading.

<Advantages of the Invention> An advantage of the present invention is that, since the specialized knowledge of calibration is built in, it is not necessary to acquire the specialized knowledge, and even an amateur can perform the calibration accurately.

Since the main work of the calibration can be performed by this device, the user can reduce the working time of the calibration work.

In addition, by automatically cutting out a phrase that needs proofreading from a Japanese sentence, referring to the proofreading dictionary only for this phrase, displaying a correct notation candidate, and allowing the user to select, This is for proofreading sentences, and it determines the necessity of proofreading for each small character string such as a bunsetsu, which not only reduces the processing time, but also allows the user to perform proofreading processing by selecting the correct notation candidates. The burden on the user for the calibration process is reduced. In addition, it is possible to extract mistakes that are often overlooked by humans, such as the mistakes of katakana “f” and hiragana “he”, which is effective in improving the accuracy of calibration.

Further, by combining with a device such as a word processor, a series of re-work such as printing and copying caused by proofreading can be omitted, and it can be expected that the efficiency of document creation work is improved.

Also, since the character string to be replaced is displayed in the original sentence, the position of the character string to be proofread, the replacement character string itself can be easily identified, and the relation with the whole sentence can be easily grasped, so that the efficiency of the proofreading work is improved. .

[Brief description of drawings]

FIG. 1 is a block diagram of the device of the present invention, FIG. 2 is a diagram showing an example of a character string input by an input means, FIG. 3 is a diagram showing an example of a dictionary, and FIG. 4 is an example of grammatical information. FIG. 5 is a diagram showing an example of a proofreading dictionary, FIG. 6 is a schematic flow chart of processing, and FIG. 7 is a diagram showing a display example of proofreading candidates. 1 is an input means, 2 is an input character storage means, 3 is a dictionary storage means, 4 is a grammar storage means, 5 is a control means, 6 is a proofreading dictionary storage means, 7 is a display means, and 8 is a selection means.

 ─────────────────────────────────────────────────── ─── Continued front page (72) Nobuo Nakamura 22-22 Nagaike-cho, Abeno-ku, Osaka-shi, Osaka Prefecture Sharp Corporation (72) Mikio Osaki 22-22 Nagaike-cho, Abeno-ku, Osaka City, Osaka Incorporated (56) References JP-A-59-127137 (JP, A)

Claims (1)

[Claims] 1. A dictionary means for storing a headline and grammatical information of the headline, a grammar means for storing a connection relation of the headline or the grammatical information of the dictionary means, and a notation that does not meet the criteria and an notation that does not meet the criterion. A proofreading dictionary means for storing the corresponding correct notation, a storage means for storing the sentence, a dividing means for dividing the sentence stored in the storage means into temporary clauses, and a temporary division divided by the dividing means. For each clause, referring to the dictionary means and the grammar means, first judging means for judging whether or not the temporary clause is a normal clause; and if it is not a normal clause by the first judging means. In response to the judgment, the tentative phrase is referred to by the proofreading dictionary means and the grammar means to judge whether the tentative phrase becomes a normal phrase by proofreading of the proofreading dictionary. Second determining means for In response to the judgment that the bunsetsu is a normal bunsetsu, the display means for displaying the temporary bunsetsu and the correct notation candidate of the tentative bunsetsu of the proofreading dictionary means are displayed on the display means. A Japanese sentence proofreading device, comprising: a selection unit for selecting a desired notation from the candidates.