JPH07160715A - Multilingual translation device - Google Patents

Multilingual translation device

Info

Publication number
JPH07160715A
JPH07160715A JP5306753A JP30675393A JPH07160715A JP H07160715 A JPH07160715 A JP H07160715A JP 5306753 A JP5306753 A JP 5306753A JP 30675393 A JP30675393 A JP 30675393A JP H07160715 A JPH07160715 A JP H07160715A
Authority
JP
Japan
Prior art keywords
language
input
means
translation device
input language
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
JP5306753A
Other languages
Japanese (ja)
Inventor
Osamu Nishida
収 西田
Original Assignee
Sharp Corp
シャープ株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Sharp Corp, シャープ株式会社 filed Critical Sharp Corp
Priority to JP5306753A priority Critical patent/JPH07160715A/en
Publication of JPH07160715A publication Critical patent/JPH07160715A/en
Pending legal-status Critical Current

Links

Abstract

PURPOSE:To provide the multilingual translation device which eliminates a need for a user to designate the language of an input sentence. CONSTITUTION:A language discriminating part 1, a language analysis part 2, a language conversion part 3, and a language generating part 4 are provided, and the language discriminating part 1 consists of the input language automatic discriminating means which automatically discriminates the language of the input sentence. The input language automatic discriminating means is provided with the means which compares the input language with translation object languages of the translator by a set of characters representing the input language to discriminate the input language, the means which compares the input language with elements of a high-frequency word list to discriminate the input language, and the means which discriminates the input language by referring to a conversion dictionary in the language analysis part.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a translation device for processing an input sentence such as analysis, conversion, generation, etc., and translating it into another language. The present invention relates to a multilingual translation device that translates between these plural languages.

[0002]

2. Description of the Related Art A conventional multilingual translation apparatus has a dedicated input / output terminal for each language, or a method in which a user specifies a language to be input by menu selection or the like. In such a system, the input means for each language is activated by selecting a menu or activating a dedicated terminal, and characters in each language can be input.

[0003]

However, such a method is effective in the case of translating in a conversational manner, but in the case of translating a sentence containing a mixture of sentences of various languages into a language at one time. Is useless. Also, like English and German,
There is an inconvenience that the menu and the terminal have to be changed even when the sentences of different languages can be expressed by using the same character set.

Further, in the case of a system in which the selection of the language to be translated and the activation of the input means are not linked, for example, when the device providing the input device and the device providing the translation are different, the same selection must be made twice.

Therefore, it is an object of the present invention to provide a multilingual translation apparatus in which the user does not need to specify the language of the input sentence.

[0006]

To achieve the above object, a multilingual translation apparatus of the present invention comprises a language determination unit, a language analysis unit, a language conversion unit and a language generation unit, and the language of an input sentence A language judgment unit is provided which is composed of input language automatic judgment means for automatically judging.

Further, the input language automatic determination means determines the input language by comparing the input language with the translation target language of the translation device using a character set representing the input language, and the input language and the high-frequency word list. It is provided with means for judging the input language by comparing it with the elements, and means for judging the input language by looking up the conversion dictionary of the language analysis unit.

As a method for determining the language, first, the character code of the input character is examined to determine what kind of character set is used. Since the character set designation, the character encoding method, and the character restoration method are internationally widely standardized by standardization organizations such as ISO and JIS,
The present invention is also premised on using such a system. Next, when there is a possibility that the same character set may be used in a plurality of languages, the language is determined by checking a match with a characteristic word of each language, for example, a particle having a high frequency of appearance, an article, a preposition, or the like. Further, when there is no match with the element of such a high-frequency word list, the dictionary lookup of the language analysis unit of machine translation is activated, and the language is determined depending on whether the dictionary lookup is successful.

[0009]

In the multilingual translation apparatus of the present invention, the user can perform translation from one language to another language by the input language automatic determination means as described above without the user designating the language of the input sentence. .

[0010]

EXAMPLE One of the examples of the apparatus of the present invention is shown. Figure 1
FIG. 3 is a block diagram of a multilingual translation apparatus for Japanese, English, French, and German according to the present invention.

Reference numeral 1 is a language determination unit for determining the language of the input sentence. Since it is the core of the present invention, it will be described in detail later. A language analysis unit 2 analyzes the structure of the input sentence according to the grammar of the sentence language. A language conversion unit 3 converts the structure of the analysis result into an internal structure of another language according to a conversion dictionary between two languages. Reference numeral 4 is a language generation unit that creates a sentence according to the grammar of the output language.

Reference numeral 5 is a conversion dictionary which describes the structure and vocabulary correspondence between Japanese and English. Reference numeral 6 is a conversion dictionary that describes the structure and vocabulary correspondence between Japan and France. Reference numeral 7 is a conversion dictionary which describes the structure and vocabulary correspondence between Japan and Germany. Reference numeral 8 is a conversion dictionary which describes the structure and vocabulary correspondence between English and French. Reference numeral 9 is a conversion dictionary that describes the structure and vocabulary correspondence between English and German. Reference numeral 10 is a conversion dictionary that describes the structure and vocabulary correspondence between German and French. Each of these conversion dictionaries can be used bidirectionally between two languages.

Reference numeral 11 is a high-frequency word list used in the language determination unit.

Reference numeral 12 is a Japanese grammar rule, which is commonly used for analysis and generation. 13 is an English grammar rule, which is required for both parsing and generation. Reference numeral 14 is a French grammar, which is shared by analysis and generation. Reference numeral 15 is a grammar rule of German, which is shared by parsing and generation. The grammar mentioned here includes both dictionaries and syntax rules.

The method shown here is based on the method of multilingual translation based on vocabulary driven bidirectional translation, and is described in the document Proceedings of COLLING 92.
(1992), Peter Whitelock, "S.
hake and BakeTranslation ”
, Known as the Shake and Bake system.

Here, it is assumed that the relationships among the Japanese, English, German, and French languages, the character sets, and the encoding methods are as shown in the table. The JIS character set for representing Japanese is JI
An escape sequence for specifying the character set of S is added, but for other character sets, it can be determined by whether or not the 8th bit is used. Also, A
The SCII character set is a subset of the LATIN-1 character set.

[0017]

[Table 1]

FIG. 2 is a flow chart showing the flow of processing of the language determination unit 1 for the sentence thus encoded and input.

In step S1, JIS is added at the beginning of the code sequence.
Determines if there is an escape sequence that specifies a character set.

In step S2, a LATIN-1 character or an ASCII character set is estimated depending on whether the 8th bit of the code is used.

In step S3, the language is determined using a high-frequency word list of English, French, and German. If there is even one match between the input sentence and the elements of the high-frequency word list, it is assumed that the language of the sentence can be estimated.

The step S4 is a process in the case where the word of the input sentence does not match the element of the high-frequency word list of any language. The dictionary look-up module of the language analysis unit is activated and the dictionary for the English grammar is started. Whether it is English or not is judged by whether or not the pulling is completed normally.

FIG. 3 shows an example of a list of English high-frequency words used by the language determination unit 1 of FIG. The language is determined by checking the match between the words of the input sentence and the elements of such a list of high-frequency words.

[0024]

Since the multilingual translation apparatus of the present invention is provided with the input language automatic judging means, it is possible to save the user the trouble of designating the input language and improve the usability of the multilingual translation apparatus. did it.

[Brief description of drawings]

FIG. 1 is a block diagram of a multilingual translation apparatus of the present invention.

FIG. 2 is a flowchart showing a processing flow of a language determination unit.

FIG. 3 is a diagram showing an example of an English high-frequency word list.

[Explanation of symbols]

 1 language determination unit 2 language analysis unit 3 language conversion unit 4 language generation unit 5 Japanese-English conversion dictionary 6 Japanese-French conversion dictionary 7 Japanese-German conversion dictionary 8 English-French conversion dictionary 9 English-German conversion dictionary 10 German-French conversion dictionary 11 Frequent word list 12 Japanese grammar rules 13 English grammar rules 14 French grammar rules 15 German grammar rules

Claims (2)

[Claims]
1. A multilingual translation device for translating between a plurality of languages, comprising a language determination unit, a language analysis unit, a language conversion unit, and a language generation unit, wherein the language of an input sentence is automatically determined. A multilingual translation device comprising a language determination unit configured by input language automatic determination means.
2. An input language automatic determination means for determining an input language by comparing the input language with a translation target language of a translation device using a character set representing the input language, and elements of the input language and a high-frequency word list. A multilingual translation device comprising: means for determining an input language by comparing with the above; and means for determining an input language by looking up a conversion dictionary of a language analysis unit.
JP5306753A 1993-12-07 1993-12-07 Multilingual translation device Pending JPH07160715A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP5306753A JPH07160715A (en) 1993-12-07 1993-12-07 Multilingual translation device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP5306753A JPH07160715A (en) 1993-12-07 1993-12-07 Multilingual translation device

Publications (1)

Publication Number Publication Date
JPH07160715A true JPH07160715A (en) 1995-06-23

Family

ID=17960902

Family Applications (1)

Application Number Title Priority Date Filing Date
JP5306753A Pending JPH07160715A (en) 1993-12-07 1993-12-07 Multilingual translation device

Country Status (1)

Country Link
JP (1) JPH07160715A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0927939A1 (en) * 1997-12-29 1999-07-07 Xerox Corporation Method and system to obtain data for information retrieval
US6246976B1 (en) 1997-03-14 2001-06-12 Omron Corporation Apparatus, method and storage medium for identifying a combination of a language and its character code system
US8326597B2 (en) 2009-01-30 2012-12-04 Kabushiki Kaisha Toshiba Translation apparatus, method, and computer program product for detecting language discrepancy

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6246976B1 (en) 1997-03-14 2001-06-12 Omron Corporation Apparatus, method and storage medium for identifying a combination of a language and its character code system
EP0927939A1 (en) * 1997-12-29 1999-07-07 Xerox Corporation Method and system to obtain data for information retrieval
US6396951B1 (en) 1997-12-29 2002-05-28 Xerox Corporation Document-based query data for information retrieval
US8326597B2 (en) 2009-01-30 2012-12-04 Kabushiki Kaisha Toshiba Translation apparatus, method, and computer program product for detecting language discrepancy

Similar Documents

Publication Publication Date Title
JP5535379B2 (en) Japanese virtual dictionary
US5268839A (en) Translation method and system for communication between speakers of different languages
KR100890691B1 (en) Linguistically intelligent text compression
US4831529A (en) Machine translation system
EP0399533B1 (en) Machine translation system and method of machine translation
EP0932871B1 (en) Methods and apparatus for translating between languages
DE60029732T2 (en) Phrase translation method and system
JP4554273B2 (en) Method and system for training a mechanical translator
US4962452A (en) Language translator which automatically recognizes, analyzes, translates and reinserts comments in a sentence
US5005127A (en) System including means to translate only selected portions of an input sentence and means to translate selected portions according to distinct rules
US6246976B1 (en) Apparatus, method and storage medium for identifying a combination of a language and its character code system
US5161105A (en) Machine translation apparatus having a process function for proper nouns with acronyms
US5890103A (en) Method and apparatus for improved tokenization of natural language text
EP0424032B1 (en) Naturel language processing apparatus
US6125342A (en) Pronoun semantic analysis system and method
EP0926604A2 (en) Translationmethod and system
KR970012111A (en) A Chinese text input computer, a Chinese text input computer, a Chinese text input computer, a Chinese text input computer, a Chinese text input computer, a Chinese text input computer, a Chinese text input computer, Program storage device
US5678051A (en) Translating apparatus with special display mode for supplemented words
US20030101046A1 (en) Word, expression, and sentence translation management tool
JP2732563B2 (en) Machine translation method and apparatus
US8209166B2 (en) Apparatus, method, and computer program product for machine translation
JP2002082945A (en) Tokenizer for natural language processing system
KR900005899B1 (en) Article drawing up devices
JPH06314294A (en) Method and device for mechanical translation
JP2892548B2 (en) Automatic translation device