JPS63163956A - Document preparation and correction supporting device - Google Patents

Abstract

PURPOSE:To make it easy to confirm and correct a part related to a numeral by extracting the part related to the numeral from a sentence by a morpheme analysis, and displaying it in a form to be easily confirmed. CONSTITUTION:A Japanese character string inputted by an inputting and editing means 1, is stored in an input character storing means 2. The character string stored in the said storing means 2 is given a morpheme analysis by a control means 5 by using a dictionary stored in a dictionary storing means 3 and a gramma stored in a gramma storing means 4, and the part of the morpheme related to the numeral is extracted. Then, the extracted part related to the numeral is displayed on a displaying means 6 so as to be distinguished from other part of the sentence. Thus, the confirmation of the part related to the numeral in the sentence, and the correction of it by a correcting means 7 are easily performed.

Description

[Detailed description of the invention] <Industrial application field> The present invention extracts parts related to numbers from Japanese text by morphological analysis, and creates documents that facilitate confirmation and proofreading. -Relates to calibration support equipment.

Conventional Technology Currently, Japanese word processors are in practical use, and related basic technologies such as Japanese input/output, editing, kana-kanji conversion algorithms, and dictionary technology have been established.

Furthermore, basic techniques such as morphological analysis, syntactic analysis, and semantic analysis are known in Japanese language processing technology.

Several types of coding systems have been established to process words, and the ability to distinguish numbers from other characters is a well-known fact not limited to Japanese.

In Europe and the United States, word processors developed early on, so related technology has advanced, and devices with spell checking and spelling functions have been put into practical use.

Compared to Western words, which are written with punctuation in each word, Japanese is usually written in kanji, kana, and kanji characters without punctuation, and the lack of a thorough orthography makes it difficult to analyze. A device that automates the difficult calibration has not yet been put into practical use.

Traditionally, when accurate Japanese was required, multiple people read together in pairs to identify problematic points, or people with specialized proofreading knowledge carried out sequential cross-checking. In addition, calibration methods are also used.

Recently, devices for supporting such calibration work are being developed. These devices can be broadly classified into two types.

One is for the former, which is a proofreading system that analyzes kanji, kana, and kana text, converts it into audio, and then reads it back to the machine via audio! It is placed in l position.

The other one is for the latter, and is aimed at supporting automation of proofreading or specialization of proofreading. Since this device requires more advanced technology than the former device, there are only conceptual proposals, and there are few reports on the means for configuring the device or the specific means for calibration.

In addition, in language processing research, K
WIC (Key Word In C.

Techniques related to (ntext) are common.

In areas other than language processing, technology related to work stage windows has been established, and devices using multi-line windows have been put into practical use to improve work efficiency.

<Problems to be Solved by the Invention> In recent years, Japanese word processors have become widespread, and more and more documents are being created with these devices. An increasing number of word processors are adopting the easy-to-enter Kana-Kanji conversion method (hereinafter, unless otherwise specified, this includes the Romaji-Kanji conversion method).

The Kana-Kanji conversion algorithm is based on a probabilistic basis, but it has some validity because in the process of converting Kana to Kanji, it is checked against linguistically supported information such as word dictionaries and grammar. has been confirmed.

However, when it comes to the numbers themselves, there is no dictionary to check them, and the input numbers are accepted as they are and sentences are created. Therefore, the numbers themselves have lower accuracy than the word parts. It has nothing but accuracy.

In addition, when numbers are connected before and after numbers, such as under 18 years of age or under 18 years of age, it is necessary to include them in the proofreading, and the method of extracting only the numbers is insufficient.

As mentioned above, even in the case of devices with a calibration function that are being developed recently, there have been no reports of a function that focuses on checking and calibrating the numerical part.

For example, a device with a voice reading function breaks down and converts a sentence into a string of simple characters and reads them out using a speech synthesizer, which makes it possible to rigorously check even numbers, but the processing speed is slow. The drawback was that it was slow.

Furthermore, this device requires additional devices such as a voice synthesizer and a speaker, which has the disadvantage of increasing costs.

Furthermore, this device requires processing related to language and speech, which has the drawback of complicating the processing and increasing the capacity of the program.

In addition, there is a problem of noise caused by the sound, and in order to eliminate the problem, a hand-on is required, and it takes time and effort to install it.

On the other hand, in the method using morphemes, syntax, and semantic analysis, W1 ability to proofread numerical errors has not been reported, and as before, the numerical part must be extracted from the sentence, checked, and then proofread. However, this method has the drawback of requiring a lot of burden and time on the workers.

In addition, a problem common to both methods is that numbers often have great meaning in documents, but there is no reported function to extract and confirm the numerical part, and it is not possible to confirm only the numerical part. When doing this, there was a drawback that the efficiency of the work was reduced.

The method of the present invention extracts parts related to numbers from sentences by morphological analysis, displays them in a form that is easy to check, and allows the user of the device to easily proofread.
This is an attempt to solve this problem.

Means for Solving the Problems> The present invention provides a means for inputting and collecting Japanese words, a means for storing the input Japanese words, a means for storing a dictionary, and a means for storing a grammar. , N control means such as a microprocessor for extracting characters/symbol strings to be proofread from the input Japanese, means for displaying the text and the candidate characters/symbol strings, and characters/symbols to be proofread. and means for correcting the character if there is a column.

<Action> Morphological analysis is performed from the Japanese input into a computer etc. using an input method, and forms related to numbers are analyzed! ! It extracts the plain parts and displays them so that they can be distinguished from other parts of the text, making it easier to confirm whether the parts related to numbers are correct or incorrect.

When the extracted part is indicated with a pointing device such as a cursor, a KWIC with the numerical part as a key is created and displayed in a separate location, making it easier to confirm whether the part related to the number is correct or incorrect. It works like this.

When there are multiple number parts in a sentence, a function is added that makes it possible to specify only the extracted part by using information that distinguishes the number part from other parts of the sentence, and then It works to confirm the correctness of the part.

In the above confirmation process, if it is confirmed that there is a mistake in the extracted part, please check the original text or KWI.
It works by correcting the incorrect parts in C using the input m collection function and proofreading the text.

By using the above-mentioned confirmation and correction functions, the numerical part can be efficiently corrected and the above-mentioned problems can be improved.

<Example> The present invention will be described in detail below based on the drawings. FIG. 1 is a block diagram of a Japanese grammar proofing device according to the present invention.

In the figure, 1 is a means for inputting and editing Japanese character strings.

2 is a means for storing the Japanese character string inputted by the input means. A keyboard is usually used as the input means, but it is also possible to use an external storage means such as a floppy disk or magnetic tape for storing input Japanese character strings without sequential input. That is, there may also be a configuration in which 1 is omitted.

3 is a means for storing a dictionary for morphologically analyzing the Japanese character/symbol strings multiplied by 2 above.

4 is used for the same purpose and is a means for storing grammar and other dictionaries.

Reference numeral 5 denotes a control means that extracts the numerical part from the character string stored in 2, stores intermediate results, and commands display. The control means includes means for storing results obtained by the control.

Reference numeral 6 denotes display means such as a CRT for displaying input character strings, intermediate results of verification, character strings to be proofread, KWIC, and the like.

7 is a proofreading means for correctly reflecting the correction results in the original text when there is an error in the KWIC displayed by 6.

FIG. 2 is an example of the character string input by 1, and shows the state displayed in 6 by means of 111ITl1 in 5. This sentence is numbered 8. *This sentence is false; the correct answer is [Total sales for fiscal year 1986 are scheduled to be 1 trillion yen. Suppose it is J.

That is, it is assumed that the number "61" is incorrect and "62" is correct. After being correctly proofread, the text will be marked 9 to distinguish it from 8.

FIG. 3 shows an example of a display according to the present invention.

This figure shows an example of the result of extracting the number part 910 from text 8 and displaying it to distinguish it from the others.

Figure 4 is an example of another display of the present invention using KWIC, and Figure 6 shows an example of the state when a pointing device such as a cursor is placed on the number string that appears first in 10. 11 is the part corresponding to the keyword in KWIC, and 12 is the entire KWIC.

FIG. 5 shows an example of the contents of the word dictionary. 13 is a heading, 14 is information indicating the distinction between an independent word or an attached word, and 15 is information on a part of speech or classification. The number 14 indicates that it is an attached word, and that it is an independent word.

Figure 6 shows an example of the grammar. 16 represents the conditions of the clause. [ ] indicates that the elements inside are essential conditions for the clause to be established. Other elements may be omitted.

FIG. 7 shows information for assembling morphemes to form phrases. Reference numeral 17 indicates a preceding morpheme, 18 indicates a subsequent morpheme, and 19 indicates information as to whether or not a character string obtained by connecting these morphemes satisfies the clause end condition.

FIG. 8 shows information for extracting a numeric string and displaying it to distinguish it from others. 20 is a character, 21 indicates the row position on the display screen where the character exists, and 22 indicates the column position. Further, 23 is information for distinguishing whether it is a numeric string or not. 24 is information that describes the start and end points of a number string and is used when creating a KWIC or the like. It doesn't matter what you want as long as you can distinguish it from others, but to make the explanation easier to understand, let's use the starting point of the number sequence, 4, as S, and the ending point as E (.

FIG. 9 shows that a specific position 25 on the display device can be described by M and H row and column numbers.

FIG. 10 is a schematic 70-diagram of the present invention. The example sentence in Figure 2, 8, will be described in detail below.

First, input IIA! The total sales amount for fiscal year 1961 is expected to be 1 ryo yen, which was input using means 1. ” is stored in the input character storage device 2. 26 is this processing block.

Each input string is checked against a word dictionary and grammar to determine morpheme elements. 27 is a processing block for word dictionary comparison. Here, as a result of the word dictionary search, the process proceeds to the 0th order "61" where it is found that "Showa" can be a noun or a prepositional particle.

We can tell from the character code that this is a number.

Therefore, we add grammatical matching. This processing block is 2
8. 27.28, there are cases where both dictionary and grammar matching succeeds and cases where they fail. If it fails, please contact the error department J! ! ! 35 is performed, and processing moves on to the next character. In process 28, using FIG. 7, elements of the preceding morpheme and the following form! ! Check whether there is a connection between elementary elements. In this case, in the case of a noun, the clause ends with "Showa", and in the case of a prefix, the provisional character string ends in "Showa 61". Next, we proceed to the processing of "year" and perform a similar process to find out that this is a suffix and can be connected to "61". Next, we move on to the processing of "no". the result,
I can see that "of 1986" is one phrase0
In the case of the noun ``Showa,'' the clause ends at ``Showa,'' and ``61
``of the year'' becomes the next clause. In such cases, the longest match method is known, which reduces the number of clauses and selects the candidate with the longest character string. As a result, "19861" is selected. The processing block 29 determines this library.

The order of collation of the codes of the input character string is not particularly fixed, and the present invention will not be affected by starting with any character.
1..."I'm thinking.

According to 27.28.29, the symbol S was added to the 24 of the character ``Show'' in ``Showa...'', and the symbol E was added to the 24 of the ``degree'' of ``1 year'', and ``Showa 61 It can be seen that "Year" is a single number string.

Similarly, it can be seen that ``1 trillion yen'' is a string of numbers.

30 is a shape! ! ! This is a processing block for determining the end of elementary analysis processing. If there is a subsequent character, it is called into the control device and prepared for morphological analysis.
This process is repeated until there are no more subsequent characters.

If a subsequent string exists, call that string,
Set it on the stack. This processing block is designated as 31.

32 is a processing block that displays the numeric string in the original text to distinguish it from others based on the result of the stack in which the information shown in FIG. 8 is saved after the character judgment process is completed.

33 is another method of extracting and displaying a numeric string. That is, it is a processing block that generates a KWIC using a number string as a key.

34 is a processing block that checks the number string and if there is a mistake, corrects it and performs collection of Ii. In this, the number "61" is corrected to "62".

After checking, you can finish the series of tasks.

Next, examples of implementation means other than those described above will be described.

In FIG. 8, the information describing the distinction between numbers and other characters and the information representing the start and end of a numeric string are stored separately in 23 and 24, but a configuration in which they are shared is also conceivable.

Also, in the above explanation, after extracting the number string in the original text, KW
IC was created, but it does not need to be done in this order; in other words, there is a method that extracts only the numerical part of the original text and does not generate or display KWIC, or
Another possible method is to generate a WIC and then extract a number string from the original text.

The extracted number string may be displayed in a uniform manner, or only a portion indicated by a cursor or the like may be displayed, and the present invention is not affected by either method.

In addition, there are two ways to proofread numbers: directly on the extracted numbers in the original text, or on keywords in KWIC and incorporating the results into the original text. However, this does not affect the present invention.

Furthermore, although the above explanation shows an example of arithmetic numerals, the same method can be applied to Chinese numerals, Arabic numerals, etc.

In addition, the word dictionary in Figure 5 has attached words and independent words in one structure, but this is to simplify the explanation, and unlike ordinary morphological analysis, independent words, affixes, attached words, etc. Even if the configurations are differentiated, the present invention is not affected.

<Effects of the Invention> The effects of the present invention are that only the numeric parts can be extracted from documents in which numbers have important meanings, making it easier to check and proofread.

Further, according to the present invention, since the numerical part is reliably extracted, it is effective in increasing the accuracy of proofreading.

Furthermore, since it is possible to extract not only numbers but also numeric strings including prefix particles, particle particles, postfix particles, etc., it is effective in further improving the accuracy of numeric proofreading.

Furthermore, since the effort of extracting numerical parts from the original text can be saved, it is effective in shortening the processing time for proofreading and reducing the mental burden and fatigue of the person doing the proofreading.

Another advantage is that there is no need for special equipment such as a voice reading device, a speaker, or a voice synthesis device.

Further, there is no need to attach a special device such as a head 7-on, and there is an advantage that the effort of attaching the device and the purchase of the device can be omitted.

Further, complicated processing such as language processing and speech processing is unnecessary, and it is effective in terms of processing program creation, maintenance, and storage capacity.

Furthermore, since it can be executed with simple processing, it is effective in terms of high processing speed.

Also, since it does not include elements that cause noise such as voices, there is no need to consider the impact on the surroundings.8! It is effective in that it allows you to install and work on machines.

[Brief explanation of the drawing]

It is. 1... Input/Jg collection means... Input character storage means 3... Dictionary storage means 4... Grammar storage means 5... Control means 6... Display means 7... Proofreading means 8 ... Example sentences containing errors 9 ... Correct example sentences 10 ... Numerical parts in sentences 11 ... Keywords in KWIC 12 ... KWIC as a whole 13 ... Headings in word dictionary 14 ...・Independent word and attached word distinction information in the word dictionary 15・
...-' Part of speech in the I-word dictionary, distinction information 16... Clause establishment condition 17... Leading morpheme 18... Following morpheme 19... Clause end condition 20... Character stack for screen display 21 ...Row position stack for screen display 22...Column position stack for screen display 23...Number judgment stack for screen display 24...Number string judgment information stack 25...Identification on the display device Position 26... Input character string IF product heat processing block 7... Word dictionary matching processing block 28... Grammar matching processing block 29... Clause determination matching processing block 30... Morphological analysis end processing block 31. ...Next character processing block 32...Number string extraction and display processing block 33...Number string KWIC display processing block 34...Proofreading processing block 35...Error processing block Agent Patent attorney Takeshi Sugiyama (et al.) 1 person) ” Figure 1 Figure 2 Figure 3 Figure 3! m5 figure 6 figure 7 figure f: tSs figure f59 figure 10

Claims (1)

[Claims] 1. A means for inputting and editing Japanese, a means for storing the input Japanese, a means for storing a dictionary, a means for storing grammar, and a method for proofreading from the input Japanese. Means for extracting character/symbol strings, sentences and candidate characters/symbols
Extracting morphemes related to numbers in a document processing system having means for displaying symbol strings, etc., and means for correcting the characters/symbol strings when there are characters/symbol strings to be proofread,
A document creation/proofreading support device characterized by making proofreading easier.