JP2738386B2 - Kana-Kanji conversion device - Google Patents

Description

Description: BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a kana-kanji conversion apparatus for converting a Japanese sentence inputted by a kana into a kana-kanji mixed sentence. 2. Description of the Related Art In recent years, kana-kanji conversion devices have been widely used in various Japanese processing devices such as a Japanese word processor as the most common means for inputting Japanese. By the way, since there are many homonyms in Japanese words, it is difficult to use a kana-kanji conversion device to uniquely convert a Japanese sentence entered in kana into a sentence mixed with kana-kanji. It is well known that this is often the case. [0004] Therefore, in order to reduce the operation of selecting a homonym performed by the user, a means for storing usage information of the homonym selected in the past by the user is provided, so that the usage of the homonym can be reduced. Methods have been devised for displaying the words in ascending order and displaying the homonyms in order from the most recently used. [0005] However, since the above-described method is based on performing kana-kanji conversion on a word basis, when attempting to perform kana-kanji conversion on a phrase basis, It had the following problems. In other words, in a conventional kana-kanji conversion device that can convert a kana-kanji string into a kana-kanji-mixed sentence in word units or phrase units, a kana-kanji-mixed sentence obtained by performing a kana-kanji conversion on the same input kana string is From a grammatical point of view, there are cases where there are two types of conversion results: one consisting of an independent word alone and one having an attached word connected to the independent word. For example, two types of conversion results are obtained for an input kana sequence "Kaleha", "Kyoto" (independent word) (Kyoto) "hi" (independent word (he) + auxiliary word (ha)). At this time, according to the conventional method, when the user selects "dead leaf", the word "dead leaf" has a higher priority in the homonyms reading "kareha", while "he If "" is selected, the word "he" in the homonyms reading "kare" has a higher priority. In other words, in the conventional method, when the above two types of conversion results are considered, the priority of the homonym can be determined between the conversion results belonging to the same type. It cannot be determined whether or not should be displayed with priority. Therefore, even if the user always selects the conversion result “He” for the input kana string “Kareha”, the next time he tries to convert the input kana string “Kaleha” again, “He” There is a problem that the conversion result is not always displayed with priority. The present invention has been made to solve the above problems. [0009] An input means for inputting kana characters, a basic dictionary for storing notation for reading and grammatical information, and a plurality of kanji kana character strings for input kana character strings A kana-kanji conversion means for outputting a group of conversion candidates from the basic dictionary, a selection means for selecting a character string from a plurality of candidates by the kana-kanji conversion means, and a character string selected by the selection means. A learning dictionary that stores independent word notation, and additional word information indicating whether or not an independent word is included. The kana-kanji conversion means reads the independent word in the character string in the conversion candidate group, and displays the independent word for the reading. , Appendix information indicating whether or not an appendix is included,
A kana-kanji conversion apparatus is characterized in that the information in the learning dictionary is compared, the conversion candidate group is rearranged according to the comparison result, and output as a plurality of candidates. According to the above-described configuration, a plurality of obtained conversion results can be displayed in order of the highest priority in an order that is optimal for the user. (Embodiment 1) Hereinafter, an embodiment of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram of a kana-kanji conversion device according to an embodiment of the present invention. In FIG. 1, reference numeral 1 denotes a means for inputting a Japanese kana string and a desired output character from a plurality of kana-kanji mixed output character strings obtained by performing a kana-kanji conversion on the input kana string. Means for selecting a column. 2 is an input device 1
This is an input kana sequence storage unit for storing the input kana sequence. Reference numeral 3 denotes a kana-kanji conversion control unit that reads a kana string from the input kana string storage unit 2 and generates a character string mixed with kana-kanji characters. Reference numeral 4 denotes a word storage unit that stores words that can be independent words other than particles and auxiliary verbs in association with their readings, kanji notation, and part of speech information. Reference numeral 5 denotes a grammar information storage unit that stores information about a set of adjuncts composed of particles and auxiliary verbs and connection information between words. 6 is a reading of words used by the user among words stored in the word storage unit, a kanji notation, and additional word additional information indicating whether an additional word was added to the word at the time of use. Is a word use information storage unit for storing. Note that the word information is stored in the word use information storage unit 6 by moving the already stored word information backward by one word and storing the word information used at the latest time in the resulting empty area at the beginning. So that the more recently used words are stored in a position closer to the beginning. Reference numeral 7 denotes a priority order of a pair of an input kana string generated by the kana-kanji conversion control unit 3 in which a delimiter is inserted at a boundary between an independent word and an adjunct and an output character string mixed with kana-kanji obtained by the kana-kanji conversion. The output character string storage unit stores the character strings in descending order. The output character string storage 7 has an area for storing priority information for each output character string. Reference numeral 8 denotes a display device that displays output character strings stored in the output character string storage unit in descending order of priority. Reference numeral 9 denotes the word information of the selected word in the word use information storage unit 6 when one set of output character strings is selected from the set of output character strings displayed on the display device 8 via the input device 1. This is a word use information updating unit to be stored. The operation of the kana-kanji conversion device configured as described above will be described below with reference to the flowchart shown in FIG. (A) The pseudonym string input by the user from the input device 1 is stored in the input pseudonym string storage unit 2. (B) The kana-kanji conversion control section 3 executes the following operation. The kana string is read from the input kana string storage unit 2, the word storage unit 4 searches for words whose word reading matches part or all of the input kana string, and those words are stored in the grammar information storage unit 5. After determining whether or not a correct output character string can be constructed using the set information of the attached words and the connection information between words, for the grammatically correct output character string, the independent words and the attached words The input kana string with a delimiter inserted at the boundary and the output character string mixed with kana / kanji are paired and sequentially stored in the output character string storage unit 7. (C) The kana-kanji conversion control unit 3 converts the set of output character strings stored in the output character string storage unit 7 in (b) using the word information stored in the word use information storage unit 6. Sort in descending order of priority. The sorting procedure will be described in detail below. First, for all output character strings stored in the output character string storage unit 7, the reading of the independent word portion of the output character string and the kanji notation are extracted. Here, the reading of the independent word portion is obtained from the input kana string up to immediately before the delimiter, and the kanji notation of the independent word is obtained from the output character string containing kana and kanji immediately before the delimiter. It is. Further, it is checked whether or not there is an attached word after the extracted independent word, based on whether or not a kana remains after the delimiter of the input kana string. Next, with respect to all the output character strings, the reading of the independent word extracted by the above operation, the kanji notation, and the word information consisting of the three items of the additional information of the adjunct word and the word information stored in the word use information storage unit 6 are performed. Perform a comparison to see if there is a match. At this time, the comparison of the word information is started from the beginning of the word use information storage unit 6. If the word information does not match, the comparison with the next word information is sequentially performed. After storing the stored position in the word use information storage unit 6 in the priority information storage area of the corresponding output character string in the output character string storage unit 7, the word information of the next output character string is compared. To do. If all word information comparisons have been completed and it is found that there is no matching word information, a specific numerical value indicating the lowest priority is stored in the priority information storage area of the corresponding output character string in the output character string storage unit 7. After storing, the process proceeds to the comparison of word information for the next output character string. When the word information matching check is completed for all the output character strings in this way, the output character string stored in the output character string storage unit 7 is finally given priority by the priority information stored in the word information matching check. Sort in descending order. Rearrangement is performed so that priority information values are arranged in ascending order. (2) Output character string storage unit 7 in display device 8
The output character strings mixed with kana and kanji stored in are displayed in order from the one stored at the beginning without the separator. (E) From the set of output character strings displayed on the display device 8, in the output character string storage unit of a set of output character strings to which the user has given a selection instruction using the input device 1. Is transmitted to the word use information updating unit 9. (F): The word use information updating unit 9 (E)
The output character string selected by the user is recognized on the basis of the position information in the output character string storage unit 7 obtained in step (1), and the same independent word reading and kanji as those extracted in (c) are recognized for the output character string. Word information consisting of three terms, notation and additional word additional information, is stored at the head of the word use information storage unit 6. When the word information is stored, the previously stored word information is moved backward by one word. At this time, if the word information has already been stored in all areas of the word use information storage section 6, the last word information is deleted. The word information used in the word use information storage unit 6 is accumulated by repeating the one-time execution of the kana-kanji conversion from (a) to (to) and obtained in the subsequent kana-kanji conversion. It will be used effectively when determining the priority of output strings. The operation has been described above with reference to the flowchart of FIG. 2. In order to make the operation more concrete, the operation mainly performed by the kana-kanji conversion control unit 3 will be described with reference to FIGS. An example will be described. FIG. 3 is a diagram showing the storage state of the word storage section 4, and shows portions where the reading, the kanji notation, and the part of speech information are stored for words having the readings of "sei" and "seika", respectively. . FIG. 4 is a diagram showing a storage state of the word use information storage unit 6, which also shows a portion in which word information on independent words read as "sei" and "seika" is stored. FIGS. 5 to 7 are diagrams showing the storage state of the output character string storage unit 7, which is stored in the output character string storage unit 7 when the kana-kanji conversion conversion is performed on the input kana string "Seika". It shows a change in state. FIG. 5 shows the contents stored in the output character string storage unit 7 immediately after the processing of the flowchart (b) is executed. Here, an output character string determined to be grammatically correct obtained by referring to the word information and the grammar information storage unit 5 shown in FIG. 3 from the word storage unit 4 is stored.
FIG. 6 shows the output character string storage unit 7 at the time when the match check between the word information stored in the word usage information storage unit 6 and the word information in the output character string is completed in the execution of the process of the flowchart (c). And shows that the priority information obtained by the above matching check is newly stored in the priority information storage area. FIG. 7 is a diagram showing the storage state of the output character string storage unit 7 immediately after the execution of the processing of the flowchart (c) is completed, and shows that the output character strings are rearranged in descending order of priority. I have. Here, referring again to FIG. 5, the input kana string "
"Independent word (sei) +
It can be seen that two types of output character strings of the attached word (power) and the independent word (Seika) are obtained. On the other hand, FIG.
From the storage content of the word usage information storage unit 6 of the above, the pronunciation used in the type with the attached
It can be seen that the surname "" and "true" are obtained, and that the reading used in the type consisting of the independent word without the attached word is "seika", and the word "birthplace" is obtained. The output character strings having the contents shown in Fig. 5 are rearranged in descending order of priority on the basis of, and the state shown in Fig. 7 is obtained.
In the state of FIG. 7, the output character strings of the type of “independent word + attached word” and “independent word” are stored separately, but in the state of FIG. It can be seen that the output character strings are stored in order. As described above, according to the present embodiment, the words used in the past are stored in the word use information storage unit 6 as “independent words +
When the input kana string is subjected to kana-kanji conversion, "independent word + auxiliary word" is stored by distinguishing whether it was used in the type of "attached word" or "independent word".
Even when two types of output character strings, that is, "independent word" and "independent word" are obtained, the output character strings can be displayed on the display device 8 in order from the output character string having the highest priority regardless of the difference between the types. In the present embodiment, the word use information storage unit 6 is configured so that the most recently used word has priority, but the word use information storage unit 6 is stored in the word storage unit 4. A configuration may be adopted in which words having a high use frequency, such as storing the frequency of use of each type by distinguishing between two types of words, "independent word + auxiliary word" and "independent word", are given priority. As described above, according to the present invention, words used in the past are grammatically viewed in two types, that is, "independent words +
The two types of "independent word + auxiliary word" and "independent word" for the same kana string are stored by distinguishing which type is used, "attached word" or "independent word". Can be displayed in the order that is optimal for the user regardless of the difference in their types, even if is obtained as an output character string for Kana-Kanji conversion. There is something.

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a block diagram of a kana-kanji conversion apparatus according to an embodiment of the present invention. FIG. 2 is a flowchart showing an operation of the kana-kanji conversion apparatus according to an embodiment of the present invention. FIG. 4 is a diagram showing the storage state of the word storage unit. FIG. 4 is a diagram showing the storage state of the word use information storage unit. FIG. 5 is a diagram showing a change in the storage state of the output character string storage unit. FIG. 7 is a diagram showing a change in the storage state of the unit. FIG. 7 is a diagram showing a change in the storage state of the output character string storage unit. [Description of References] 1 input device 2 input kana string storage unit 3 kana-kanji conversion control unit 4 word storage unit 5 Grammar information storage unit 6 Word usage information storage unit 7 Output character string storage unit 8 Display device

Claims (1)

(57) [Claims] Input means for inputting kana characters, a basic dictionary for storing notation and grammatical information for reading, and a kana kanji for outputting from the basic dictionary a plurality of conversion candidate groups as kanji kana mixed character strings for the inputted kana character strings Conversion means, a selection means for selecting a character string from a plurality of candidates by the kana-kanji conversion means, and whether or not the character string selected by the selection means includes an independent word reading, an independent word notation for reading, and an auxiliary word A learning dictionary that stores attached word information indicating whether or not the kana-kanji conversion means reads an independent word in a character string in the conversion candidate group, an independent word notation for the reading, and whether or not an included word is included. comparing the information in the supplied word information and Manabu習辞document showing, based on the result of comparison, the group
The conversion candidates outputted from the dictionary SORT parallel, kana-kanji conversion apparatus and outputs a plurality of candidates.