JPH07104863B2 - Kana-Kanji converter - Google Patents

Description

TECHNICAL FIELD The present invention relates to a kana-kanji conversion device for converting a Japanese sentence input by a kana code or the like into a kana-kanji mixed sentence and outputting it.

[Conventional technology]

In a conventional kana-kanji conversion device for converting a Japanese kana sentence input by key input or the like into a kana-kanji mixed sentence, the conversion target is fixed to a spoken word or a sentence word. But,
When both letters and quotes are mixed, only one of them (usually only spoken) is supported, which is inconvenient.

In addition, when both of them are mixed and converted, this cannot be done because it causes a lot of ambiguity in the sentence analysis.

[Problems to be solved by the invention]

In contrast to the above-mentioned conventional technique, since it is desired to convert both the spoken language and the spoken language without introducing ambiguity in the sentence analysis, it is necessary to switch and process them. For this purpose, two dictionaries are required. It is intended to do rationally.

[Means for solving problems]

In order to solve the above-mentioned problems, a kana-kanji conversion device of the present invention refers to a dictionary storing a word heading and a word candidate corresponding to the word heading, and an input kana character string with reference to the dictionary, and word segmentation. In the kana-kanji conversion device for converting the kana character string into a kana-kanji mixed sentence, the kana-kanji conversion device is provided with specification means for designating kana-kanji conversion of colloquial words or kana-kanji conversion of sentence words. A clause area storing a headline and a word candidate corresponding to the colloquial word heading, and a sentence word area storing a sentence word heading and a word candidate corresponding to the sentence word heading; Is a conversion switching unit that switches between conversion by colloquial words and conversion by sentence words based on the designation by the designating unit; and The colloquial language processing means for referring to the colloquial area of the dictionary for word headings cut out from the kana character string, and segmenting the kana character string into phrases based on the referenced word candidates and grammatical rules of colloquial words; When switching to conversion by a sentence word by the switching means, the sentence word area of the dictionary is referred to for the word heading cut out from the kana character string, and the kana is obtained based on the referred word candidate and the grammatical rule of the sentence word. And a word processing means for writing a character string into sub-clauses.

[Operation] The kana-kanji conversion device of the present invention configured as described above
A clause processing means, a colloquial area storing a colloquial word heading and a word candidate corresponding to this colloquial word heading, and a sentence word area storing a sentence word heading and a word candidate corresponding to this colloquial word heading; The input kana character string is segmented into phrases by referring to a dictionary including.

The operator designates either kana-kanji conversion of colloquial words or kana-kanji conversion of sentence words by the specifying means. The conversion switching means included in the clause processing means switches between conversion by colloquial words and conversion by sentence words based on the designation by the designating means. The colloquial word processing means included in the phrase processing means refers to the colloquial area of the dictionary for a word heading cut out from the input kana character string when the conversion switching means switches to the conversion by the colloquial word, and the referred word candidate Based on the grammatical rules of colloquial language, the kana character string is segmented into phrases. The word processing means included in the clause processing means refers to the word area of the dictionary for the word heading cut out from the input kana character string when the conversion switching means switches to the conversion by the word, and the referenced word candidate Based on the grammatical rules of the sentence and the grammar, the kana character string is segmented into sentences.

[Examples] Here, details of the present invention will be described below based on illustrated examples.

FIG. 1 is a diagram showing an embodiment of a kana-kanji conversion device of the present invention. Reference numeral 1 in the figure is a central processing unit that controls the entire system based on data input from an input unit 2 (keyboard or the like). The character string and the control code read by the input unit 2 are sent to the kana-kanji conversion device 8 for kana-kanji conversion.

The kana character string taken in by the kana character input unit 9 is automatically detected by the phrase delimiter unit 10 in the dictionary expansion section 11 while verifying the possibility of mutual connection from the independent word dictionary, the auxiliary word dictionary, and the word test unit. Phrase segmentation is performed, Kana-Kanji candidates are created for each segment, and the segment candidate output unit 13 stored in the segment candidate storage unit 12 outputs.

At this time, according to the sentence word / spoken word switching unit 14 specified by the spoken word / sentence word switching specification unit 7, the spoken word / spoken word switching unit 14 makes a spoken word independent word dictionary 15, a common use independent word dictionary 17, a spoken word exclusive Word dictionary 18, Commonly used accessory dictionary 20, Colloquial language test unit 22
In the case of a sentence word, the sentence word independent word dictionary 15, the commonly used independent word dictionary 17, the colloquial auxiliary word dictionary 18, the commonly used auxiliary word dictionary 20, and the sentence word verification unit 22 are selected and used.

When these analyzes are completed, the Kana-Kanji candidate selection unit 3
The phrase candidate output unit 13 outputs a phrase candidate group in response to a display request from the phrase candidate display unit 4, the phrase candidate display unit 4 displays the display unit 5, the Kana / Kanji candidate selection unit 3 selects a candidate, and the phrase candidate determination unit 6 determines the candidate. To do.

Here, to give an example, for example, [where,
The following sentence appears first in the book. If you want to input the sentence "Old boy boy", first, use the colloquial / sentence word switching designation unit 7 to make a switch to input the colloquial language.

Then, the colloquial sentence "Here, the next sentence comes first" is input by the input unit 2. The kana character is input by the kana character string input unit 9 and the bunsetsu delimiter 10 stores the bunsetsu candidate in the bunsetsu candidate storage 12 while using the dictionary expansion unit 11. In the dictionary expansion unit 11, the collation test unit 22 the spoken word adjunct dictionary 18, the commonly used adjunct dictionary 20, the colloquial independent word dictionary 15, and the commonly used independent word dictionary 17 are used for analysis by the switch. Are set as described above, analysis is performed as a colloquial language, candidates are sequentially output from the phrase candidate output unit 13 in units of phrases, and the candidates are displayed on the display unit 5 by the phrase candidate display unit 4, and the kana-kanji candidate selection unit 3 and the phrase candidates are confirmed. The unit 6 can convert the sentence into a desired kana-kanji mixed sentence.

Next, if you enter "Mukashio Noko Arikari" in colloquial words, the sentence words "boy" and "Arikari" will not be converted correctly, and an erroneous conversion such as "old-fashioned saw kick" will be performed. Then, next, the spoken language / sentence word switching designation unit 7 makes a switch for inputting a sentence word.

Then, the word sentence “Mukashio no Korekari” is input from the input unit 2. This kana character is taken in by the kana character string input unit 9 and is extracted by the phrase delimiter unit 10 into a dictionary expansion unit.
In this dictionary expansion unit 11, which stores the phrase candidates in the phrase candidate storage unit 12 while using 11,
The sentence test unit 21, the sentence-specific auxiliary word dictionary 19, the common-use auxiliary word dictionary 20, the sentence-specific independent word dictionary 16, the common-use independent word dictionary 17 are set to be used for analysis, and are analyzed as sentence words. Candidates are sequentially output from the phrase candidate output unit 13 in units of phrases, displayed on the display unit 5 by the phrase candidate display unit 4, and can be converted into a desired Kana-Kanji mixed sentence by the Kana-Kanji candidate selection unit 3 and the phrase candidate determination unit 6. It will be a matter.

FIG. 2 is a flow chart showing the operation of the embodiment of the present invention.

First, in <200>, the colloquial sentence switching unit 7 designates which is to be performed. Here, SW is set to 0 for colloquial words, and SW is set to 1 for sentence words. And <201>
Input the kana character string to be converted by, but the previous SW is 0
If so, grammar processing of colloquial language and colloquial dictionaries <203>
The colloquial translation of <202> is performed otherwise, and the grammatical processing of the sentence and the dictionary conversion of <202> are performed, and <204>
Use ＞ to display the phrase candidates and <205
Repeat this while selecting with>.

According to the kana-kanji conversion device of the above-described embodiment, the dictionary 1 for searching a word according to the instruction from the colloquial / sentence word switching designation unit 1
Since 5, 16 and 18, 19 and the test units 21, 22 are switched, it is possible to appropriately write a kana character string consisting of colloquial words or sentence words into bunsetsu and perform kana-kanji conversion.

〔The invention's effect〕

According to the kana-kanji conversion device of the present invention described above, since the area of the dictionary to be referred to is changed by switching between conversion by colloquial words and conversion by sentence words by the conversion switching means, based on the grammatical rules of colloquial words or the grammatical rules of sentence words. Kana-Kanji conversion can be performed while appropriately writing a Kana character string consisting of colloquial or sentence words into bunsetsu.

[Brief description of drawings]

FIG. 1 is a functional block diagram showing an outline of a kana-kanji conversion device according to an embodiment of the present invention. FIG. 2 is a flow chart showing the operation of the present invention. 18 …… Adjective dictionary for colloquial words 19 …… Adjective dictionary for sentence words

Claims (1)

[Claims] 1. A kana character string, comprising: a dictionary storing a word heading and a word candidate corresponding to the word heading; and a phrase processing means for writing an input kana character string into phrase segments with reference to the dictionary. In a kana-kanji conversion device for converting kana-kanji mixed sentences, a kana-kanji conversion for colloquial words or a kana-kanji conversion for sentence words is provided with a specifying means, and the dictionary includes word headings of colloquial words and word candidates corresponding to the word headings of the colloquial words. And a word area storing a word heading of the sentence word and a word candidate corresponding to the word heading of the sentence word, the clause processing means, based on the designation by the designating means, Conversion switching means for switching between conversion by the word conversion and conversion by the sentence word, and when the conversion switching means switches to conversion by the colloquial words, the word heading cut out from the kana character string is A collaborative processing unit that refers to the colloquial area of the dictionary and punctures the kana character string based on the referred word candidates and collaborative grammatical rules, and the conversion switching unit switches to conversion by sentence words. At this time, a word processing unit that refers to the word area of the dictionary for word headings cut out from the kana character string, and performs word segmentation of the kana character string on the basis of the referred word candidates and grammatical rules of the word. A kana-kanji conversion device that is equipped with.