Machine translation device, method of processing data, and program

• US 9,002,695 B2
• Filed: 05/12/2004
• Issued: 04/07/2015
• Est. Priority Date: 05/12/2003
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Watanabe, Hideo, Kanayama, Hiroshi
• Primary Examiner(s): ADESANYA, OLUJIMI A
• Application Number:
  US10/843,748
• Publication Number:
  US 20050010421A1
• Time in Patent Office: 3,982 Days
• Field of Search: 704/1, 704/2, 704/3, 704/8, 704/9, 704/10, 704/277
• US Class Current: 704/2
• CPC Class Codes: G06F 40/169 Annotation, e.g. comment data or footnotes
• CPC Class Codes: G06F 40/55 Rule-based translation

Abstract

Provided are two types of translation engines. One of the translation engines translates a text written in a source language X into an intermediate language C, and the other translates the intermediate language C into a target language Y. The X-C translation engine translates an original text written in the source language X into a text in a predetermined intermediate language C as well as acquires and adds annotations obtained by this translation to the translated text written in the intermediate language C. The C-Y translation engine references annotations, which are obtained by the X-C translation engine and added to the text in the intermediate language C, and translates the text in the intermediate language into a text in the target language Y sentence.

Claims

1. A machine translation device comprising:

a first translation engine for translating an original text written in a source language into a text in a natural intermediate language, and for acquiring and adding annotations obtained by the translation to the translated text in the intermediate language, said annotations comprising at least a source language annotation; and

a second translation engine for translating the text in the intermediate language into a text in a target language by referencing the annotations added to the text in the intermediate language; and

first and second bilingual dictionaries, wherein the second translation engine translates from the intermediate language to the target language using a first dictionary for the source language to the target language based on the source language annotation in addition to a second dictionary for translating from the intermediate language to the target language.

2. The machine translation device according to claim 1, wherein the second translation engine outputs both a translation from the source language to the target language made based on the source language annotation and a translation from the intermediate language to the target language made without using the source language annotation as translation results.

3. The machine translation device according to claim 1, wherein the first translation engine writes the text in the intermediate language in a document file of a predetermined markup language and writes the annotations in the document file as commands for the markup language.

4. The machine translation device according to claim 1, further comprising a translation result modification unit for outputting translation results made by the second translation engine, accepting a user selection processing for the outputted translation results from a user, and reflecting the processing in the translation results.

5. The machine translation device according to claim 1, wherein said first translation engine comprises a plurality of first translation engines which correspond to a plurality of the source languages.

6. The machine translation device according to claim 1, wherein said second translation engine comprises a plurality of second translation engines which correspond to a plurality of the target languages.

7. The machine translation device according to claim 1, wherein the annotations include further annotation data comprising at least one of scope of a word, modification data on words, scope of a sentence, alternative interpretation data, and linguistic attributes.

8. The machine translation device according to claim 1, wherein said first translation engine provides annotations by at least one of designating annotations for parts of a sentence and adding data to selected significant parts of a sentence.

9. The machine translation device according to claim 7, wherein the second translation engine provides a first translation by referencing the further annotation data to produce annotation translation results and provides a second translation without referencing the further annotation data to produce non-annotation translation results, and wherein both translation results are outputted.

10. A machine translation device which translates a text written in a first natural language into a text in a second natural language, the machine translation device comprising:

a parse unit which parses the text written in the first language;

a syntactic transfer unit which translates syntax of the text written in the first language into syntax of the second language by using a bilingual dictionary from a third natural language to the second language based on annotations added to the text written in the first language, in addition to a bilingual dictionary for the first language to the second language; and

a text generation unit which generates the text in the second language based on processing results of the syntactic transfer unit.

11. A computer-implemented method for a computer, having at least computer processing unit and at least one component for outputting of results to a user, to automatically process data to translate an original text written in a source language into a text in a target language, the method comprising the steps of:

first translating the original text into a first translated text in a predetermined intermediate natural language, acquiring and adding annotations obtained by the translation to the first translated text in the intermediate language, and storing the first translated text in the intermediate language in a predetermined computer storage means, wherein the annotations include at least a source language annotation; and

second translating the first translated text in the intermediate language stored in the predetermined computer storage means into the second translated text in the target language by referencing the annotations added to the text in the intermediate language, a bilingual dictionary for the source language to the target language based on said source language annotation and a bilingual dictionary for the intermediate language to the target language, and outputting the second translated text as translation results in the target language.

12. The method of processing data according to claim 11, wherein the annotations include further annotation data comprising at least one of word source annotation data, word modification annotation data, sentence scope annotation data, alternative interpretation annotation data and linguistic attribute annotation data and wherein the second translating step comprises translating by referencing the further annotation data to produce annotation translation results and translating without referencing the further annotation data to produce non-annotation translation results, and wherein both translation results are outputted in the second step.

13. The method of claim 11 wherein said acquiring and adding annotations obtained by the translation to the first translated text in the intermediate language comprises at least one of designating annotations for parts of a sentence and adding data to selected significant parts of a sentence.

14. The method of claim 11 wherein the second translating step outputs both a translation from the source language to the target language made based on the source language annotation and a translation from the intermediate language to the target language made without using the source language annotation as translation results.

15. The method of claim 11 further comprising receiving at least one of user modification and user selection input in response to output of translation results.