Bilingual authoring assistant for the “tip of the tongue” problem

• US 7,827,026 B2
• Filed: 12/21/2004
• Issued: 11/02/2010
• Est. Priority Date: 12/21/2004
• Status: Expired due to Fees

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Dymetman, Marc, Segond, Frederique, Brun, Caroline
• Primary Examiner(s): Hudspeth; David R
• Assistant Examiner(s): Spooner; Lamont M
• Application Number:
  US11/018,758
• Publication Number:
  US 20060136223A1
• Time in Patent Office: 2,142 Days
• Field of Search: 704 2- 8, 715/255, 715/264, 715/265
• US Class Current: 704/2
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation

Abstract

A bilingual authoring apparatus includes a user interface (20) for inputting partially translated text including a text portion in a source language and surrounding or adjacent text in a target language. A bilingual dictionary (34) associates words and phrases in the target language and words and phrases in a source language. A context sensitive translation tool (30, 32, 38) communicates with the user interface, receives the partially translated text, and provides at least one proposed translation in the target language of the text portion in the source language. The at least one proposed translation in the target language is derived from the bilingual dictionary based on contextual analysis of at least a portion of the partially translated text.

Claims

1. A bilingual authoring apparatus comprising:

a user interface for inputting partially translated text including a text portion in a source language and surrounding or adjacent text in a target language;

a bilingual dictionary associating words and phrases in the target language and words and phrases in a source language; and

a context-sensitive translation tool communicating with the user interface, the context sensitive translation tool receiving the partially translated text and providing at least one proposed translation in the target language of the text portion in the source language, the at least one proposed translation in the target language being derived from the bilingual dictionary based on contextual analysis of at least a portion of the partially translated text, wherein the context-sensitive translation tool includes a semantic dictionary lookup module performing a monolingual contextual analysis of the text portion in the source language conditional upon the text portion in the source language including more than one word or category.

2. The bilingual authoring apparatus as set forth in claim 1, wherein the semantic dictionary lookup module further performs bilingual contextual analysis of the partially translated text conditional upon the text portion in the source language including only a single word or category.

3. The bilingual authoring apparatus as set forth in claim 1 wherein the context-sensitive translation tool includes:

a parser;

wherein conditional upon the text portion in the source language including only a single word or category, the context-sensitive translation tool applies the parser to the partially translated text to guess a part-of-speech of the text portion in the source language, the at least one proposed translation in the target language being selected from the bilingual dictionary to be consistent with the guessed part-of-speech.

4. The bilingual authoring apparatus as set forth in claim 3, wherein the bilingual dictionary stores example source language contexts including the text portion in the source language and corresponding target language translations, and the context-sensitive translation tool further includes:

a bilingual text comparator that compares the corresponding target language translations with the surrounding or adjacent text in the target language, the at least one proposed translation including a corresponding target language translation that matches at least one of lexically and semantically with the surrounding or adjacent text in the target language.

5. The bilingual authoring apparatus as set forth in claim 3, wherein the bilingual dictionary stores source language collocations of the text portion in the source language, and the context-sensitive translation tool further includes:

a collocation comparator that (i) determines translations in the target language of the source language collocations using the bilingual dictionary, and (ii) compares the determined translations with the surrounding or adjacent text in the target language, the at least one proposed translation including a determined translation in the target language of a source language collocation that corresponds with the surrounding or adjacent text in the target language.

6. The bilingual authoring apparatus as set forth in claim 5, wherein the collocation comparator further (iii) identifies target language synonyms of the determined translations in the target language, the comparing (ii) further comparing the target language synonyms with the surrounding or adjacent text in the target language.

7. The bilingual authoring apparatus as set forth in claim 1, wherein the user interface includes:

a display showing authored text including at least the partially translated text; and

a user input device for indicating the partially translated text and for sending the indicated partially translated text to the context-sensitive translation tool.

8. The bilingual authoring apparatus as set forth in claim 1, wherein the user input device is a pointing device, the user indicating the partially translated text by highlighting the partially translated text displayed on the display using the pointing device.

9. The bilingual authoring apparatus as set forth in claim 1, wherein the user interface is a word processor.

10. A bilingual authoring method comprising:

receiving from an associated user partially translated text including a text portion in a source language and surrounding or adjacent text in a target language;

identifying the partially translated text;

deriving at least one proposed translation in the target language of the text portion in the source language based on contents of a bilingual dictionary and contextual analysis of at least a portion of the partially translated text, wherein the deriving of at least one proposed translation in the target language includes performing a monolingual contextual analysis of the text portion in the source language conditional upon the text portion in the source language including more than one word or category, wherein the deriving is performed by a.computer; and

displaying the at least one proposed translation to the associated user.

11. The bilingual authoring method as set forth in claim 10, wherein the deriving of at least one proposed translation in the target language further includes:

performing a bilingual contextual analysis of the partially translated text conditional upon the text portion in the source language including only a single word or category.

12. The bilingual authoring method as set forth in claim 10, wherein the deriving of at least one proposed translation in the target language further includes:

determining that the text portion in the source language includes only a single word or category;

responsive to the determining, parsing the partially translated text to guess a part-of-speech of the text portion in the source language; and

selecting the at least one proposed translation in the target language from translations provided in the bilingual dictionary that are consistent with the guessed part-of-speech.

13. The bilingual authoring method as set forth in claim 12, wherein the bilingual dictionary stores example source language contexts including the text portion in the source language and corresponding target language translations, and the deriving of at least one proposed translation in the target language further includes:

comparing the corresponding target language translations with the surrounding or adjacent text in the target language to identify at least one proposed translation as a corresponding target language translation matching at least one of lexically and semantically the surrounding or adjacent text in the target language.

14. The bilingual authoring method as set forth in claim 13, wherein the comparing further includes:

identifying target language synonyms of words of the corresponding target language translations in attempting to semantically match the corresponding target language translations and the surrounding or adjacent text in the target language.

15. The bilingual authoring method as set forth in claim 12, wherein the bilingual dictionary stores source language collocations of the text portion in the source language, and the deriving of at least one proposed translation in the target language further includes:

determining translations in the target language of the source language collocations using the bilingual dictionary;

comparing the determined translations with the surrounding or adjacent text in the target language to identify at least one proposed translation as a determined translation in the target language of a source language collocation corresponding with the surrounding or adjacent text in the target language.

16. The bilingual authoring method as set forth in claim 15, wherein the determining of translations further includes:

identifying target language synonyms of the determined translations in the target language.

17. The bilingual authoring method as set forth in claim 10, wherein the displaying of the at least one proposed translation to the associated user includes:

displaying at least a portion of an entry of the bilingual dictionary corresponding to a word of the text portion in the source language; and

highlighting portions of the displayed entry corresponding to the at least one proposed translation.