JPH0578058B2 - - Google Patents

Description

[Detailed description of the invention]

The present invention relates to a kana-kanji conversion processing device used in Japanese word processors, etc. In particular, when there are homophones and allographs (hereinafter referred to as "homonyms"), the present invention has a function for learning homophones in units of phrases, so that the operator can The present invention relates to a kana-kanji conversion processing device that can improve the automatic discrimination rate of homophones while reducing the burden on users. Various systems have been proposed as kana-kanji conversion processing (hereinafter also simply referred to as "conversion processing") devices. The present applicant first applied for a patent application in 1983-
The device proposed in No. 149737, ``Kana-Kanji Conversion Processing Device,'' is one such device. This device includes "a means for inputting a Japanese sentence as a kana sentence, a means for temporarily storing a character string inputted by the input means,
In a kana-kanji conversion processing device having a word dictionary storage means and a kana-kanji conversion control circuit that searches the word dictionary storage means and converts the contents of the temporary storage means into a sentence mixed with kanji, the word dictionary outputs homophone and allograph words. a word buffer memory containing ranking information and storing words extracted from the word dictionary; means for outputting the contents of the word buffer memory according to the output ranking information; and words selected from the output and output. and a homophone and allograph of the word that was output immediately before, and a means for replacing the output ranking information with the homophone and allograph of the word that was output immediately before, and the replaced output ranking information,
A kana-kanji conversion processing device characterized by having means for writing in a predetermined location of the word dictionary, and can be said to have a learning function on a word (independent word) basis. However, when trying to obtain a conversion result such as "What is fire?", the following problem arises. In other words, for the input of ``Hito wa'', an independent word dictionary such as the one shown in Figure 1 is used, and as a result, the display order of conversion candidates using the longest match method is ``Hito wa'' → ``Ichi wa''. → “What is fire” → “What is fire”, and the next candidate key (update key) must be pressed many times. The present invention has been made in view of the above circumstances, and its purpose is to solve the problems with the above-mentioned device and to provide a method that can improve the automatic discrimination rate of homophones while reducing the burden on the operator. An object of the present invention is to provide a kanji conversion processing device. The above object of the present invention is to provide means for inputting Japanese sentences as kana sentences, means for temporarily storing character strings input by the input means, means for storing a word dictionary, and means for storing the word dictionary. a kana-kanji conversion control circuit that searches and analyzes the contents of the temporary storage means in units of words or words and converts them into a sentence containing kanji; a means for displaying a conversion result by the kana-kanji conversion control circuit; and a means for displaying the conversion result. In the kana-kanji conversion processing device, the word dictionary is configured to include learning information of homophone and allograph words, and at least the word dictionary is configured to include learning information of homophone and allograph words, and at least the word dictionary is configured to include learning information of homophone and allograph words. A means is provided for storing the notation determined to include a plurality of units described in the word dictionary in correspondence with the input character string, and the storage means is given priority when searching the dictionary. This is achieved by a kana-kanji conversion processing device characterized by the following configuration. Embodiments of the present invention will be described in detail below with reference to the drawings. FIG. 2 is a block diagram of a kana-kanji conversion processing device showing one embodiment of the present invention. The device of this embodiment is
Classify the Japanese words that make up the input sentence into independent words, prefixes, suffixes, and adjunct words, break down the input sentence into division units centered on one independent word, input them in kana characters, and input the input sentences. The stored character string is stored in a temporary storage means, and the stored content is stored as the independent word,
This is an example in which the present invention is applied to a kana-kanji conversion processing device that compares each of prefixes, suffixes, and adjuncts with the contents of a dictionary that stores them. Note that in the description of this embodiment, a break-up unit (also referred to as a "bunsetsu") refers to the following. [Prefix] (Independent word) [Suffix] [Adjunct word] * Here, there must be one independent word, and the words enclosed in [ ] may be omitted; ) may be connected multiple times. In FIG. 2, 11 is an input keyboard device, 12 is an input character buffer register that temporarily stores input character strings, 13 is a control circuit, 14 is an output editor, 15 is a display device, and 16 is a It's a printer. 17 to 24 indicate dictionary documents,
17 is a connection matrix table, 18 is an independent word dictionary, 19 is a prefix table, 20 is a suffix table, 21 is a word conjugation table, 2
2 is an adjunct word table, and 23 is a katakana-hirakana correspondence table. The contents of these dictionaries will be described later. Also, 24 is an output statement register, 25, 27, 2
9 is an output buffer memory for independent words, prefixes, and suffixes, respectively; 26, 28, and 30 are rank controllers. 31 is a homophone phrase buffer memory. The specific contents of dictionaries and tables will be explained below using examples. The contents of the dictionary or table are as follows.・ Pronunciation: The part that matches the input string ・ Notation: Characters to be output when a specific word is determined ・ Part of speech, conjugation: The part of speech and conjugation of each independent word are recorded by number ・ Output order: At a certain point (1) Independent Word Dictionary 18 As shown in part of the contents in Figure 3, among independent words, nouns, Nouns (nouns that can be accompanied by the verb "suru"), verbs, adjectives, adjectives, adjectives,
Memorizes things that belong to adverbs, interjections, etc. Among these, the pragmatic word is only the stem, but the first-stage conjugated verb includes the inflexible part of the conjugated part, and the sa verb ``suru'' and the ka verb ``kuru'' include the entire conjugated form. (2) Prefix Table 19 As part of its contents is shown in Figure 4, it stores prefixes attached to independent word nouns, etc. (3) Suffix table 20 As part of its contents is shown in Figure 5, it stores suffixes attached to independent words, nouns, etc. (4) Word Conjugation Table 21 As part of its contents is shown in Figure 6, the verb, adjective, part of speech of the adjective verb, and conjugation ending are stored for each classification according to the conjugation form. Furthermore, the five-stage conjugation endings of verbs are shown in Figure 7, and the one-stage conjugation endings are shown in Figure 8.
In addition, the conjugation endings of adjectives and adjective verbs are shown in Figures 9 and 10, respectively. (5) Adjunct word classification table 22 It is composed of a major classification table 22A and a minor classification table 22B.The major classification table 22A, as part of its contents is shown in Figure 11, contains formal nouns, auxiliary verbs (formal verbs) ), auxiliary verbs, and particles, and correspond to the minor classification table 22B by number.
As part of the contents of the minor classification table 22B is shown in FIG. 12, the contents are classified by formal nouns, auxiliary verbs, conjugated forms of auxiliary verbs, and particles. (6) Connection matrix table 17 This table shows the grammatical connection relationship between independent words and adjunct words by arranging preceding words in rows and following words in columns, where element c _ij in row i and column j is It is defined as follows. (b) When cij = 1, the word in the i-th row can be connected to the word in the j-th column. (b) When Cij = 0, the word in the i-th row cannot be connected to the word in the j-th column. The contents are shown in Figure 13. A part of it was shown. In addition, the 13th
The column numbers in the figure are shown in hexadecimal numbers in groups of four columns. In addition, the serial numbers in the major classification table 22A of the attached words are:
Corresponds to the column number above. FIG. 14 shows a model of the steps for selecting adjunct words using connection matrix table 17. Furthermore, the connection matrix table 17 has an item for termination possibility, and when this is "1", it indicates that there is a possibility of termination as the clause. The operation of this embodiment configured as described above will be described below. (1) Input operation Input is performed using the keyboard device 11. Keyboard device 1
An example of the character arrangement of No. 1 is shown in FIG. 15, but the arrangement is not limited to this. This keyboard device is configured to output phrase break information by pressing a combination of a shift key and a special key marked with ◯ or □. By combining the shift key (hereinafter referred to as "○shi") and the special key, it is possible to specify the conversion mode as follows. (b) Immediately after a phrase that requires conversion into a sentence containing kanji, press ○shi, then ○kan. (Example) Keystroke order Output after conversion I am ○shi○kan→ I am Gatsukohe○shi○kan→Go to school (b) If you want to output the input phrase as hiragana or katakana, press ○shi. Press the key, then press the □flat or □piece key. (Example) Keystroke order Output after conversion Lonely ○shi□flat → Lonely school/bus○shi□piece → school bus (2) Conversion processing operation Here, we will explain what fire is. An example of creating a sentence such as ``It's something I can't live without.'' is shown below. In the following explanation, the ○shi○kan, ○shi□hei, ○shi□hata, etc. will be represented by the clause delimiter ○clause. In addition, the homophonic phrase Batsuhua 3, which is a feature of the present invention,
1, as an example of which is shown in FIG. 16, is for registering phrases that have homophones and would be displayed at a lower order in normal conversion, with corresponding pronunciations and spellings. Initially, nothing is registered in this homophone phrase buffer 31, but in the above-mentioned situation, the phrases used are registered, including their frequency, if necessary. Returning to the example sentence, the operator uses the keyboard device 11, and the person is ○ something. For a person, there is no ○ section without ○ section. When the first phrase "Hitoha" is input and the phrase delimiter information is input, first, the homophone phrase buffer 31 is searched. However, at this stage, nothing is stored in the homophone phrase buffer 31, so the routine moves on to a normal dictionary search, and as described above, the word is converted to ``hito wa''. This is not what the operator intended, so when the operator presses the update key, ``ichiwa'' is displayed, and when the operator presses the update key again, ``non-towa'' is displayed, and then ``fire is'' is displayed. . Since this is what the operator intended, the operator moves on to input the next phrase and inputs "something." This input action (strictly speaking, "Na" in "Something.")
2), the previously input "Hitowa" and its output display "Fire" are registered in the homophone phrase buffer 31. Next, upon completion of the input of "Something.", after searching the homophone phrase buffer 31 (there is no corresponding homophone phrase buffer 31), it is converted into "Something." by a normal dictionary search. Next, when "Hitoha" is input and the phrase delimiter information is input, the same sound phrase buffer 31 is searched for the character string "Hitowa". As a result, the previously stored "What is Fire" can be retrieved. Furthermore, when you enter "Hito ni to te ○ clause", after searching for the homophone phrase Batsuhua 31 with the character string "Hito ni to te", you will find "Toto ni to te" by a normal dictionary search.
The output is displayed as follows. As described above, by introducing the homophone phrase buffer 31 and referring to it first, it is possible to improve the automatic discrimination rate of homophones. In addition, in a similar example, when you want to get ``return'', ``frog'' comes first, and when you want to get ``new company (prefix + independent word)'', ``invader (independent word + suffix)'' comes first. However, by storing these in the homophone phrase buffer 31 as shown in FIG. 16, it becomes possible to perform quick conversion. As mentioned above, homophones that occur in a phrase and for which the correct answer cannot be obtained with the first candidate are registered one after another in the homophone phrase buffer 31, and when this homophone phrase buffer 31 becomes full, , it is a good idea to delete the one that has already been registered and register the latest homophone there. How to delete: (1) Delete the oldest one first. (2) Delete phrases that are used least frequently before a certain registration order (for example, half the number of registered phrases). The following methods are possible, but are not limited to these methods. In the above embodiment, phrases that would be displayed in a lower order in normal conversion processing are registered in the homophone phrase buffer 31, but in relation to the capacity of the buffer, phrases are registered as second candidates. The following or the third candidate or lower can be determined as appropriate. As described above, according to the present invention, there are provided means for inputting Japanese sentences as kana sentences, means for temporarily storing character strings input by the input means, means for storing a word dictionary, and the word dictionary. a kana-kanji conversion control circuit that searches a storage means, analyzes the contents of the temporary storage means in units of words or words, and converts them into sentences containing kanji; and means for displaying the conversion results by the kana-kanji conversion control circuit; In the kana-kanji conversion processing device having means for receiving definite information of the conversion result, the word dictionary is configured to include learning information of homophone and allograph words, and at least the final conversion result differs from the initial conversion result due to the definite information. A means is provided for storing a notation determined to include a plurality of units described in the word dictionary at word or phrase divisions in correspondence with the input character string, and the storage means is given priority when searching the dictionary. Since it is configured to search, it is possible to improve the automatic discrimination rate of homophones while reducing the burden on the operator, and it has the remarkable effect of realizing a practical kana-kanji conversion processing device.

[Brief explanation of drawings]

Fig. 1 is a diagram showing a part of an independent word dictionary, Fig. 2 is a block diagram of a kana-kanji conversion processing device that is an embodiment of the present invention, and Figs. 3 to 14 are diagrams showing the contents of a dictionary document. , FIG. 15 is a diagram showing the character arrangement of the keyboard device, and FIG. 16 is a diagram showing the contents of the homophone phrase buffer. 11... Keyboard device, 12... Input character buffer register, 13... Control circuit, 14... Output editor, 15... Display device, 16... Printer, 17
... Connection matrix table, 18 ... Independent word dictionary, 19 ...
Prefix table, 20...Suffix table, 21...Word conjugation table, 22...Adjunct word list, 23...Hiragana-katakana correspondence table, 24...Output sentence register, 31...Homophone phrase batufua.

Claims (1)

[Claims] 1. A means of inputting Japanese sentences as kana sentences,
Means for temporarily storing the character string inputted by the input means; means for storing a word dictionary; and means for searching the word dictionary storage means and analyzing the contents of the temporary storage means in units of words or words to obtain kanji. The kana-kanji conversion processing device includes a kana-kanji conversion control circuit for converting into a mixed sentence, a means for displaying a conversion result by the kana-kanji conversion control circuit, and a means for receiving confirmation information of the conversion result, the word dictionary is configured to include learning information for homophone and allograph words, and is determined to include at least a plurality of units described in the word dictionary at word or word divisions different from the initial conversion result based on the determination information. 1. A kana-kanji conversion processing device, comprising means for storing a notation and its input character string in correspondence with each other, and the storage means is configured to be searched preferentially when searching a dictionary.