JPS6133577A - Mechanical translator - Google Patents

Abstract

PURPOSE:To reduce the capacity of a dictionary and to reduce the load of mechanical translation by replacing a ''katakana'' (the square form of ''kana'' (Japanese syllabary) character string in an input text corresponding to a sent foreign language character string by the character string expressed by the sent foreign language and seding the replaced character string to a translation part. CONSTITUTION:A translator 1 is constituted of a preprocessing part 2 and a translation part 3 and the preprocessing part 2 replaces the ''katakana'' character string corresponding to the foreign language in an input text for Japanese character strings by alphabetically expressed English words and sends the obtained text to the translation part 3. The translation part 3 has a Japanese analysis part 4 and an English formation part 5. The Japanese analysis part 4 checks the parts of speech for words and also checks connecting relation between words and the English formation part 5 forms English words in accordance with the analyzed result of the Japanese analysis part 4.

Description

[Detailed Description of the Invention] [Field of Industrial Application] The present invention converts a katakana character string representing a foreign language in an input text into a character string written in a foreign language in preprocessing of machine translation, and then converts the text into a character string written in a foreign language. This relates to a machine translation device that sends text to a translation department.

[Prior art and problems]

In conventional machine translation devices that translate Japanese into English, katakana character strings were searched only from the Japanese word dictionary, so English words written in katakana must be registered in the Japanese word dictionary. There is. Putting English words written in katakana in a Japanese word dictionary and putting the same English words written in alphabetical letters in an English word dictionary not only increases the capacity of the dictionary but also complicates the translation process. There is a drawback to this.

[Purpose of the invention]

The present invention eliminates the above-mentioned drawbacks, and aims to provide a machine translation device that can reduce the capacity of a dictionary and reduce the load of machine translation.

[Means to achieve the purpose]

Therefore, the machine translation device of the present invention is a machine translation device that includes a preprocessing section having a katakana sequence extraction section, a dictionary access section, and a text merging section, a translation section, a Japanese dictionary, and a foreign language dictionary. , a character string written in katakana characters is written in the foreign language dictionary corresponding to a string written in foreign language characters, and the katakana extraction section sends the katakana character string in the input text to the dictionary access section. The dictionary access unit is configured to send text other than katakana character strings to the text merging unit, and the dictionary access unit checks whether or not there is a katakana character string that matches the sent katakana character string in the Japanese dictionary. , if not, check whether there is a katakana string that matches the sent katakana string in the foreign language dictionary,
In some cases, the text merging unit is configured to send a string in the corresponding foreign language character notation to the text merging unit, and the text merging unit converts the katakana character string in the input text corresponding to the sent foreign language character string. The system is characterized in that it is configured to replace the text with the received character string written in a foreign language, and send the replaced text to the translation section.

[Embodiments of the invention]

Embodiments of the present invention will be described below with reference to the drawings.

FIG. 1 is a diagram showing an outline of one embodiment of the present invention. 1st
In the figure, 1 is a translation device, 2 is a preprocessing section, 3 is a translation section, 4 is a Japanese analysis section, and 5 is an English generation section.

Translation device! 1 is composed of a preprocessing section 2 and a translation section 3. The preprocessing unit 2 replaces katakana character strings of foreign words in the input text of Japanese character strings with English words written in alpha bent notation, and sends the resulting text to the translation unit 3. The translation unit 3 includes the Japanese analysis unit 4 and the English generation unit 5.
have. Note that the input text is divided into words. The Japanese language analysis unit 4 examines the part-of-speech type of a word, and examines the relationship between words. The English generation unit 5 generates English according to the analysis result of the Japanese analysis unit 4.

FIG. 2 is a block diagram of one embodiment of the preprocessing section 2. As shown in FIG. In FIG. 2, 6 indicates a katakana extraction section, 7 a dictionary access section, 8 a Japanese word dictionary, 9 an English word dictionary, and 10 a text merging section. The katakana string extraction section 6 extracts katakana strings from the input text, sends the extracted katakana strings to the dictionary access section 7, and sends the extracted katakana strings to the text merging section 10. The dictionary access section 7 is
The Japanese word dictionary 8 is searched based on the sent katakana string, and if the corresponding word exists in the Japanese dictionary 8, the katakana string is sent as is to the text merging unit 10, and the corresponding word is searched. If the word does not exist in the Japanese word dictionary 8, the English word dictionary 9 is searched and the corresponding alphabetical English word is sent to the text merging unit 10g. The text merging unit 10 replaces the corresponding katakana string in the input text with the sent alphabetical English words, and sends the resulting text to the translation unit 3. A plurality of Japanese word records are stored in the Japanese word dictionary 8, and the Japanese word records include a header field for kana, a kanji field for storing the corresponding kanji, a field for storing the part of speech type, and a field for storing the part of speech type. It consists of a field for storing the number of times, a symbol field for storing symbols representing words, etc. The English word dictionary 9 stores a plurality of English word records, and the English word records include an alphabetical heading field, a field for storing the corresponding English word written in katakana, a field for storing the part of speech type, and a field for storing the number of usages. It consists of fields such as fields and symbol fields.

Note that Japanese-English words such as "outlet" are stored in the Japanese word dictionary 8.

FIG. 3 is a diagram illustrating the operation of the embodiment of FIG. 2. ■
When a text like ``■'' is input, a katakana string like ``■'' is sent from the katakana extraction section 6 to the dictionary access section 7, and a character string like ``■'' is sent from the katakana extraction section 6 to the text merging section ]O.
An alphavent character string such as ■ is sent from the dictionary access unit 7 to the text merging unit lO, and a text such as ■ is output from the text merging unit lO.

The translation unit 3 performs the following operations.

For example, assume that the character string "I will develop 5uper Computer+puter" is input to the translation unit 3. The Japanese language analysis unit 4 examines the part of speech type and symbol of the word in the input text. ``I'' is a pronoun, ``haj is a particle, r
Super ComputerJ has a noun, "wo" is a case particle, and "developing" is a verb.

Also, "I" is, for example, 001, and "Developer" is, for example, 0.
It has the symbol 05. Next, the Japanese language analysis section 4
"I" and "wa" form a noun clause, rsuper
We know that ComputerJ and ``wo'' form a noun clause, and we also know that the noun clause ``I am J'' relates to ``to develop,'' and the noun clause ``rSuper Computer'' also relates to ``to develop.'' The analysis results of the Japanese analysis unit 4 are passed to the English generation unit 5, and the results are passed to the English generation unit 5.
is based on this analysis result.
5uper Computer generates the English sentence J.

〔Effect of the invention〕

As is clear from the above description, according to the present invention, it is possible to achieve effects such as reducing the capacity of a dictionary and reducing the load of machine translation.

[Brief explanation of drawings]

FIG. 1 is a diagram showing an outline of one embodiment of the translation device of the present invention,
FIG. 2 is a block diagram of one embodiment of the preprocessing section shown in FIG. 1, and FIG. 3 is a diagram for explaining the operation of FIG. 2. 1... Translation device, 2... Preprocessing unit, 3... Translation unit, 4... Japanese analysis unit, 5... English generation unit, 6...
- Katakana extraction unit, 7...Dictionary access unit, 8...Japanese word dictionary, 9...English word dictionary, 10...Text merging unit.

Claims (1)

[Claims] A machine translation device comprising a preprocessing section having a katakana sequence extraction section, a dictionary access section, and a text merging section, a translation section, a Japanese dictionary, and a foreign language dictionary, wherein the foreign language dictionary includes a foreign language dictionary. A character string expressed in katakana characters is written in correspondence with the character string expressed in characters, and the katakana extraction unit sends the katakana character strings in the input text to the dictionary access unit and sends the characters other than the katakana character strings to the text merging unit. The dictionary access unit checks whether or not there is a katakana character string that matches the sent katakana character string in the Japanese dictionary, and if there is no katakana character string that matches the sent katakana character string, the dictionary access unit It is configured to check whether or not there is a katakana character string that matches the character string in the foreign language dictionary, and if so, to send the character string in the corresponding foreign language character notation to the text merging unit, and to The merging unit is configured to replace the katakana character string in the input text corresponding to the received foreign language character string with the received character string written in the foreign language, and send the replaced text to the translation unit. A machine translation device characterized by: