JP2715419B2 - Translation equipment - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION [Industrial Application Field] The present invention relates to a translator for translating Japanese into another language. [Prior Art] A conventional translator from Japanese to another language first inputs a kana-kanji mixed character string created by an editing device or the like as shown in the flowchart of FIG. 2 (S21).
Then, a morpheme and syntax analysis (S22) is performed on the input kana-kanji mixed character string. Analysis of these (S22)
Thus, the phrase, the dependency, and the main part predicate in the character string mixed with the kana-kanji are investigated. Next, language conversion processing (S23) is performed. This is a process of determining a translation word of each word in Japanese and further converting a Japanese sentence structure into a target language sentence structure. Next, a target language generation process (S24) for rearranging the word order and adding particles and the like is performed to create a translated sentence. [Problems to be Solved by the Invention] However, in the conventional translator, translation is performed only from character string data mixed with kana and kanji characters, so that a translated sentence cannot be uniquely determined. For example, for the sentence "Japanese is coming now", the morphological analysis processing (S22) analyzes "Today / this person / is coming" and "now / Japanese is coming / now". The translated sentence changes depending on whether it is analyzed as "." Also, "biology"
In the language conversion process (S23), the translated sentence changes between the case where the word "" is interpreted as "safe" and replaced with the target language, and the case where the word "name" is interpreted and replaced. As described above, since the conventional translation device cannot uniquely determine a translated sentence, there is a drawback that mistranslation occurs. [Object of the Invention] The present invention has been made to solve the above-mentioned drawbacks,
The purpose is to provide a translation device that is fast and has few translations. [Means for Solving the Problems] A translation device according to a first aspect of the present invention for achieving this object converts a Japanese sentence in which a kana character is input at each break of a phrase or the like into a kana-kanji character with reference to the break. A first conversion means for creating a kana-kanji mixed character string, a storage means for storing the kana-kanji mixed character string created by the first conversion means, together with a kana character string and the delimiter, and storage in the storage means A second conversion unit that reads out the character string mixed with the kana / kanji and converts the character string into a language other than Japanese in consideration of the kana character string and the delimiter. Further, the translation device of the second invention analyzes a Japanese sentence in which kana characters are inputted collectively to obtain a segmentation or the like, and converts the kana-kanji character with reference to the segmentation to create a character string mixed with kana-kanji characters. A first conversion means, a storage means for storing the kana-kanji mixed character string created by the first conversion means together with a kana character string and a delimiter determined by the kana-kanji conversion processing, and A second conversion unit that reads a character string mixed with kana-kanji characters and converts the character string into a language other than Japanese in consideration of the kana character string and a delimiter. [Operation] In the first invention having the above configuration, the first conversion means converts the Japanese sentence in which the kana character is input for each delimiter of a phrase or the like into a kana-kanji character by taking into account the delimiter, and converts the kana-kanji character string Create The storage means stores the kana-kanji mixed character string created by the first conversion means together with the kana character string and the delimiter. Then, the second conversion means reads the kana-kanji mixed character string stored in the storage means, and converts the kana-kanji character string and the delimiter into a language other than Japanese in consideration of the kana character string and the delimiter. In the second invention having the above configuration, the first conversion means analyzes the Japanese sentence in which the kana character is input collectively to obtain a delimiter such as a phrase, and converts the kana kanji into kana kanji in consideration of the delimiter. Create a mixed string. The storage means stores the kana-kanji mixed character string created by the first conversion means together with the kana character string and the delimiter found by the kana-kanji conversion processing. Then, the second conversion means reads the character string mixed with kana and kanji stored in the storage means, and converts it into a language other than Japanese in consideration of the kana character string and the delimiter. [Example] An example of the present invention will be described below. In FIG. 3, the microcomputer 11 includes a CPU (Central Processor Unit), a memory, an interface circuit, and the like. The microcomputer 11 is configured to function as a Japanese word processor 11a and a translator 11b by a program. A keyboard 12 is connected to the microcomputer 11. The keyboard 12 can input kana characters or Roman characters corresponding to the kana characters. The keyboard 12 is provided with various control keys,
The user uses the control key to operate the microcomputer 11
Can be given various instructions. An external storage device (storage means) 13 capable of storing data and the like is connected to the microcomputer 11. This external storage device 13 stores kana-kanji conversion, which will be described later,
Dictionary data necessary for processing such as morphological analysis is stored. The external storage device 13 can store and output various information in a file format. Also, a CRT (cathode ray tube) display 14 and a printer 15 are connected to the microcomputer 11. The operation of the translation apparatus configured as described above will be described with reference to the flowchart of FIG. First, the microcomputer 11 is a word processor
Functions as 11a. The user inputs the translated text (Japanese) using the keyboard 12 in kana or roman characters for each phrase, and instructs the kana-kanji conversion using the control key each time a phrase is input. The microcomputer 11 receives the data of the kana character string from the keyboard 12 (S3
1), referring to the dictionary data for kana-kanji conversion recorded in the external storage device 13, kana-kanji conversion (S32)
I do. At this time, the part of speech is also analyzed at the same time. If there is a homonym and a character string containing kana and kanji cannot be specified, the microcomputer 11 displays this fact on the CRT display 14 and allows the user to select it. In this way, the input kana character string is sequentially converted into a kana-kanji mixed character string, and the kana character string, kana-kanji mixed character string, phrase delimiter, part of speech information are translated into a file as translation data, and the external storage device Store it in 13. When the input of the translated sentence is completed, the microcomputer
The translation unit 11 operates as the translation unit 11b under the control of the user. The microcomputer 11 reads out the translation data stored in the external storage device 13 for each sentence and translates it for each sentence as described below. First, the microcomputer 11 performs a syntax analysis (S33) of a character string mixed with kana / kanji corresponding to the read one sentence. At this time, since the segmentation and part-of-speech information was already stored in the translation data file, there was no need to perform a new morphological analysis, and a new morphological analysis was performed on the character string containing kana-kanji characters. The syntax can be analyzed faster and more accurately than after the post-syntax analysis. Next, language conversion processing (S34) is performed. Here, the microcomputer 11 converts the Japanese sentence structure into the target language sentence structure as described above, and further converts each element of the kana-kanji mixed character string into the target language according to the dictionary data stored in the external storage device 13. (English etc.). Next, the microcomputer 11 performs a target language generation process (S35). The microcomputer 11 refers to the dictionary data stored in the external storage device 13, rearranges the replaced target language, and adds particles and the like. At this time, the data of the kana character string is stored in the file of the translation data and replaced by taking it into consideration, so that when the same kanji character has two meanings, such as “living”, “sabutsu” and “namamono” It is also possible to specify the meaning in. In the present embodiment, the part-of-speech analysis is performed at the same time as the kana-kanji conversion processing, so that higher-speed processing is possible. The present invention is not limited to the above embodiment,
Various modifications are possible. For example, in the present embodiment, the kana character string is converted into a character string mixed with kana kanji for each phrase, but it is also possible to input a plurality of phrases at a time and collectively convert kana kanji. In this case, morphological analysis is performed as kana-kanji conversion processing. Therefore, the same processing can be performed by storing the analyzed morpheme data in the translation data file. Further, in this embodiment, all the translated sentences are converted into a character string mixed with kana-kanji characters and then translated collectively. However, the translation process can be performed every time one sentence is input. Further, it is considered a modification of the present invention to individually configure a word processor capable of outputting information such as morpheme and kana character string data and a translation device that performs translation as described above based on the information. . [Effects of the Invention] As described in detail above, in the first invention, it is not necessary to perform morphological analysis when performing translation processing as in the related art. Since the delimiter is taken into consideration, the contents of the sentence mixed with kana and kanji can be accurately grasped, and there is a very practical effect that mistranslation when converted into another language can be drastically reduced. Further, in the second invention, a delimiter is obtained from the kana character string input collectively without considering the delimitation of the sentence, and the delimiter and the kana character string are stored together with the kana-kanji mixed sentence. Since the input operation can be performed quickly, and there is no need to perform morphological analysis when performing translation processing as in the past, not only can the translation processing be speeded up, but also kana character strings and delimiters are taken into account in the translation processing. This has a very practical effect that the content of a character string mixed with kana and kanji can be accurately grasped and mistranslation when converted into another language can be drastically reduced.

BRIEF DESCRIPTION OF THE DRAWINGS The drawings are for explaining the present invention, FIG. 1 is a flowchart showing the operation of an embodiment of the present invention, and FIG. 2 shows the operation of a conventional translator. Flowchart diagram, 3rd
FIG. 2 is a block diagram showing the configuration of the embodiment. In the figure, 11 is a microcomputer, 11a is a block schematically representing the operation of the microcomputer 11 as a Japanese word processor, 11b is a block schematically representing the operation of the microcomputer 11 as a translator, and 12 is a keyboard. is there.

Claims (1)

(57) [Claims] A first conversion unit that converts a Japanese sentence in which a kana character is input for each delimitation of a phrase or the like into a kana-kanji character by taking into account the delimitation to create a character string mixed with a kana-kanji character; Storage means for storing the kana-kanji mixed character string together with the kana-kanji character string and the delimiter; and reading the kana-kanji mixed character string stored in the storage means, taking into account the kana-kanji character string and the delimiter, and reading other than kana-kanji characters. A translation device, comprising: a second conversion unit that converts a language. 2. First converting means for analyzing a Japanese sentence in which kana characters are input collectively to obtain a delimiter such as a phrase and converting the kana to kanji in consideration of the delimiter to create a character string mixed with kana and kanji; Storage means for storing the kana-kanji mixed character string created by the conversion means together with the kana character string and the delimiter found by the kana-kanji conversion processing; and reading the kana-kanji mixed character string stored in the storage means, A translation device comprising: a second conversion unit configured to convert a kana character string and a delimiter into a language other than Japanese in consideration of a kana character string and a delimiter.