JPS62209663A - Correcting device for japanese sentence - Google Patents

Abstract

PURPOSE:To enable even an amateur to correct sentences with high accuracy by making use of an expression changing dictionary to extract and correct those character/symbol strings to be corrected. CONSTITUTION:A control part 5 performs collation among a character string of Japanese words stored in an input character memory means 2, a dictionary stored in a dictionary memory means 3, and a grammar stored in a grammar memory means 4 respectively to extract those parts to be possibly corrected, to store the interim result of collation and gives a command for display. An expression changing dictionary memory means 6 changes the inhibited expressions or restricted headers into the standard expressions respectively. A display means 7 displays the interim result of collation of the dictionary, the character strings to be corrected, the character strings to be replaced, etc. A selection means 8 selects the correct one out of those candidates of expression to be replaced and displayed on the means 7.

Description

[Detailed Description of the Invention] <Different industrial field> The present invention relates to a Japanese sentence proofing device that extracts and proofreads notations and expressions that do not meet specific standards from Japanese sentences. .

Conventional technology> In Europe and the United States, word processors were developed early, and related technology has advanced, and devices with spell checking and correcting functions have been put into practical use.

Compared to Western words, which are written with punctuation into each word, Japanese is usually written in kanji, kana, and kanji characters without punctuation, and the orthography is not thorough, so it is difficult to analyze. It is difficult to perform calibration, and no equipment for automating calibration has been put into practical use.

The conventional Japanese proofreading method is to have multiple people work together in pairs and read the words together, and then extract the points between them, or to have someone with specialized knowledge of proofreading conduct a series of verifications. It's a method. For the former, a proofreading system has been proposed that can analyze a text containing kanji and kana, convert it into speech, and read the text together with a machine.

However, devices for the latter are intended to automate calibration or support professionalization of calibration, and require more advanced technology. Specific means of calibration were not reported.

<Problems to be solved by the invention> Professional knowledge of proofreading is required to perform proofreading.
It took time to learn it. In addition, the number of people with specialized proofreading knowledge is small, which poses a problem when proofreading a large amount of text or when proofreading needs to be done quickly.

Also, from the perspective of an expert with knowledge of proofreading, it is necessary to pay attention to the details in order to perform proofreading correctly.
He was under a mental burden.

Despite this, there were errors that were difficult for humans to detect and errors that were easily overlooked, and the accuracy of the proofreading was poor.

Also, because Japanese has no established orthography, the same word may be written in different ways, and if names vary depending on the writer, making it difficult to read. There was a problem with the pregnancy process.

In addition, when ordinary people without specialized knowledge of proofreading create text using a word processor, etc., it is necessary to reprocess the document file by reading, printing, copying, etc. in order to proofread small mistakes. There was a problem in terms of the efficiency of the process of preparing the meeting.

In addition, there are some words that should not be used or should not be used in publications or newspapers that are visible to the public.
Failure to calibrate may result in injury or damage to others.

The present invention extracts words that are prohibited from being used or words that are preferable not to be used from Japanese sentences, and extracts the characters/symbol strings (hereinafter, characters/symbol strings may be simply referred to as character strings). The present invention attempts to solve this problem by presenting character strings to be replaced with C using a paraphrase dictionary and allowing the user of the device to select one.

Means for Solving the Problems> The present invention provides a means for inputting and editing Japanese, a means for storing the input Japanese, and a means for storing a dictionary consisting of standard notation of Japanese. a means for storing reference Japanese grammar; a control means such as a microprocessor for extracting a character string to be proofread from the input Japanese; and a character string to be replaced with the extracted character string. , means for displaying Japanese characters, and means for selecting a correct character string from among the candidate character strings.

Effects> By comparing and collating character strings in Japanese-based notation, which are input into a computer or the like using an input means, with an accumulated dictionary, some parts of the comparison are successful and some parts are not. The successfully matched parts are compared with the reference grammar table and are classified as 0,!, if both the notation and grammar meet the criteria, and if the notation meets the criteria but no grammatical connection is established. Also, portions that fail in comparison with the dictionary are classified into those that grammatically meet the standards and those that do not.

The present invention performs morphological analysis by comparing the input character string with a dictionary and a grammar table, and also compares and matches the character string cut out by the morphological analysis with a paraphrase dictionary, and if the matching is successful, proofreading is performed. Displayed as a column candidate The user of this device selects from among the candidates to be replaced.
The selection means operates to select candidates that meet the criteria.

<Example> A detailed explanation of the present invention will be given below based on the figures. FIG. 1 is a block diagram of a pro-nk of a Japanese grammar proofing device according to the present invention.

In the figure, 1 is a means for inputting Japanese character strings. 2 is a means for storing the Japanese character string inputted by the input means. The input means is usually a keyboard, but input is performed sequentially, and an external storage means for storing input Japanese character strings, such as a 70-tup disk or magnetic tape, may be used instead. It is possible. That is, there may also be a configuration in which 1 is omitted.

3 is means for storing a dictionary consisting of Japanese character strings that meet the criteria. 4 is a means of memorizing Japanese grammar 0 Japanese has no established orthography, so spelling and grammar that meet certain standards are considered correct. Below, when we refer to correct notation or grammar, we mean that it meets certain standards.

5 compares and checks the Japanese character strings stored in 2 above with the dictionary stored in 3 and the grammar stored in 4, extracts parts that may need proofreading, and stores intermediate results. It is a control means for controlling display and commanding display. The control means includes means for storing results obtained by the control.

Reference numeral 6 is a paraphrase dictionary for changing expressions whose use is prohibited or headings whose use is prohibited to expressions that meet the standards.

Reference numeral 7 denotes display means such as a CRT for displaying intermediate results of dictionary matching, character strings to be proofread, character strings to be replaced, and the like.

8 is a means for selecting a correct notation candidate from among 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 a dictionary stored in 3. 9 is a heading to be compared with the input character string. The notation of this heading is, for example, the modern kana usage by G:jn 'Ifj council,
It is based on the regulations of newspaper companies, companies, etc.

In this case, ``Uketoru'' indicates that ``Uke wa Toru'' is the standard for correct notation.

10 is part-of-speech information which is one of the grammatical information of the heading. In this way, the dictionary may contain grammatical information for grammatical processing of the heading. 611 indicates that the heading is an independent word, and 12 indicates that it is an attached word.

The conjugated JU ending in mHFJ can also become a heading by being connected to the stem of an independent word with conjugation.

13 is paraphrase flag information indicating whether the heading requires rephrasing or not. In the current example, 1 is assumed to indicate that rephrasing is necessary, and 0 is assumed to be unnecessary. 14 is paraphrase dictionary search information for matching with a paraphrase dictionary for a heading with only paraphrase flag information. For example, a pointer to the corresponding heading in a paraphrase dictionary is included.

The fjSA diagram is an example of the grammar information stored in 4.

For ease of viewing, the headings shown in the tJSz diagram are also shown. Reference numeral 15 is grammatical information that defines the connection relationship between headings or part-of-speech information expressed in 10''Ch.

For example, the stem ``Uke'' of the lower first-level verb is connected to the auxiliary verb ``ru'', and the stem ``Ukehatori'' of the fifth-level verb can be connected to the ``conjugated ending of U-line'' or the ``tsu'' sound of Hatsu. represents. 16 is a grammar that specifies whether each heading can satisfy the clause end condition, and ○ satisfies the clause end condition.
× indicates that the requirements are not met. - Figure 5 shows a paraphrase dictionary related to this patent.

17 is a notation that is prohibited or should be refrained from use, and 18 is a corresponding correct notation. 18 is the third
In some cases, it may be possible to layer the information using a pointer to the corresponding heading in the dictionary in the figure.

FIG. 6 is a schematic flow diagram of the present invention. #19 stores the input string on the stack in 5. 20 temporarily divides the W-multiplied character symbol string using a kanji code or the like. 21 reads each tentatively divided input character string. 22 compares the input character string read in 21 with the dictionary heading. In step 623, the process branches depending on whether the matching is successful or unsuccessful, and the grammatical constraints are checked for the character strings that have been successfully matched. 24 refers to the heading paraphrase dictionary flag obtained by the above morpheme processing.

25 indicates the character string successfully matched in 24, and 8 most likely character strings are displayed. 26 performs character string selection proofreading with reference to the displayed character strings. 27 examines the large input character string to be matched. 28 is a process when either the dictionary or grammar verification fails, and a separate proofreading process is performed assuming that the probability of proofreading is high.

However, since this is outside the scope of this patent, we will not discuss it in detail.

FIG. 7 is an example of proofreading candidates and replacement candidates presented by the device using the paraphrase dictionary of the present invention. Reference numeral 29 indicates a character string of a proofreading candidate extracted as a character string whose use is prohibited or whose use should be refrained from being extracted.

30 is a correct notation candidate that has been paraphrased by the paraphrase dictionary.

The actual processing flow will be described using the example sentences shown in Figure 2 and the dictionary and grammar shown in Figures 3 and 4. First, input the string ``The maid next door.Start j to 5.''

Next, the input string is temporarily divided using the code of the stacked string. As a result, "The maid next door." becomes "
Next door” and “maidservant.” Divided into J.

Next i The input character "next door" which has been divided into two parts is read into the control device 5 and compared with the dictionary headings shown in FIGS. 3 and 4. In this case, the "next" part in the dictionary matches. Next [next]
Refer to the paraphrase flag. Since the paraphrase source flag is not specified, the information for proceeding to the next process is stacked in 5, and the connection condition of the corresponding heading is compared with the next input character string. In this case, both are [of] and match.

Next, the clause end condition of the item whose heading is "no" in FIG. 3 is checked at 16 in FIG. 4. 16, in this case, the clause end condition is satisfied, and the minute is 9, and ``next'' is stacked at 5 as a normal clause.

Next, the process proceeds to the "maid." part. Similar to ``next door'', by comparing the words ``maid'' and ``maid'' in the dictionary, ``maid'' in the dictionary matches. ``The maid J satisfies the phrase termination condition according to 16 in the tJSJ diagram, so ``the maid'' is considered a normal phrase.
Stack on. Further, the paraphrase flag information for "maid" is referred to using the same procedure as above. Since the + times are specified in the flag, search the paraphrase dictionary ('i7 report) and search for the paraphrase word 1, ``maid''. '' can be displayed as shown in Figure 7.The upper part of this figure is for ``maid'' and the lower part is for ``neighborhood''. If there are multiple character strings, you can choose to display them all at once, as shown in this figure, or to display them one by one.

The user of the device can use a selection means such as a keyboard to calibrate the notation to the required notation from among the candidates of notations to be replaced.

<Effects of the Invention> The effects of the present invention are that since specialized knowledge of proofreading is built-in, there is no need to learn specialized knowledge (:), and even amateurs can perform proofreading with high accuracy. That is 1
The main work of calibration can be done with this device, making it convenient.
This allows personnel to spend less time on proofreading work.

In addition, it is possible to automatically extract character strings that need proofreading from Japanese texts, and use a proofreading dictionary to present character strings to be replaced and display them separately, making it easier for proofreaders. It is effective in reducing fatigue and mental burden.

Furthermore, it is also possible to extract errors that humans tend to overlook, such as the mistake between ``he'' in katakana and ``he'' in hiragana, which is also effective in improving the accuracy of proofreading. Furthermore, by combining it with a device such as a word processor, it is possible to omit a series of reworks such as printing and copying caused by proofreading, and it is expected that the efficiency of document creation work will be improved.

In addition, a paraphrase dictionary can extract expressions that are prohibited from being used or expressions that are specified to be refrained from using, and convert them into expressions that should be rephrased, thereby reducing the damage caused by using such words. It can be prevented.

[Brief explanation of drawings]

tJS1 is a block diagram of the configuration of the device of the present invention, FIG. 2 is a diagram showing an example of a character string input manually using an input means, FIG. 3 is a diagram showing an example of a dictionary, and FIG. 4 is a diagram showing an example of grammatical information. Figure 5 is a diagram showing an example of a paraphrase dictionary, Figure ft5a is a schematic flow diagram of processing, and Figure tlIJ7 is a diagram showing an example of displaying paraphrase 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, 8 is a selection means Agent Patent attorney Takeshi Sugiyama (1 other person) Figure 1 Figure 3 Figure 5 Figure 7 Figure 6

Claims (1)

[Claims] A means for inputting and editing Japanese, a means for storing the input Japanese, a means for storing a dictionary consisting of standard notation of Japanese, and a means for storing the grammar of the standard Japanese. , characters to be proofread from the input Japanese.
a means for extracting a symbol string; a means for storing candidates for a character/symbol string to be replaced with the extracted character/symbol string; a means for displaying the candidate character/symbol string; What is claimed is: 1. A Japanese grammar proofing device having a means for selecting a correct character/symbol string from a Japanese grammar dictionary, which uses a paraphrase dictionary to extract and proofread a character/symbol string to be proofread.