Language selection for information retrieval

• US 8,862,595 B1
• Filed: 11/18/2011
• Issued: 10/14/2014
• Est. Priority Date: 11/23/2010
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Lim, Yew Jin, Kojoukhov, Alexandre, Tan, Hui, Heymans, Maureen, Chin, Jeffrey, Cho, Sung-Jung
• Primary Examiner(s): BROWN, SHEREE N
• Application Number:
  US13/300,364
• Time in Patent Office: 1,061 Days
• Field of Search: 707/749
• US Class Current: 707/749
• CPC Class Codes: G06F 16/3337 Translation of the query language, e.g. Chinese to English

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for cross-language information retrieval. In general, one aspect of the subject matter described in this specification can be embodied in methods that include the actions of receiving a query in a source language, the query including one or more query terms; automatically determining one or more target languages relevant to the query; translating the query into one or more translated queries in the respective one or more target languages; determining search results responsive to the respective one or more translated queries; and providing one or more of the search results.

Claims

1. A method performed by data processing apparatus, the method comprising:

receiving a query in a source language, the query including one or more query terms;

determining one or more target languages relevant to the query using one or more language scores associated with each of the one or more query terms, wherein determining one or more target languages relevant to the query includes;

identifying terms related to the query

for each related term, determining a language score for each of a plurality of languages;

combining the language scores for each related term for each respective language of the plurality of languages; and

determining one or more target languages relevant to the query, other than the source language, as corresponding to languages of the plurality of languages having a combined language score beyond a threshold score;

translating the query into one or more translated queries in the respective one or more target languages;

determining search results responsive to the respective one or more translated queries; and

providing one or more of the search results.

2. The method of claim 1, further comprising:

combining the determined search results for the one or more queries into a single ordered list of search results.

3. The method of claim 1, wherein the providing includes translating the determined search results into the source language.

4. The method of claim 3, further comprising:

selectively providing an original language search result for presentation corresponding to a provided translated search result, where the original language search result is provided for presentation below the translated search result, and where original language search results are provided independently according to user selection.

5. The method of claim 1, wherein identifying a language score for each related term includes identifying the related term in a table that maps a plurality of terms to corresponding pre-computed language scores.

6. The method of claim 1, wherein the related terms are terms that are likely to co-occur with one or more query terms.

7. A system comprising:

one or more computing devices operable to perform operations comprising;

receiving a query in a source language, the query including one or more query terms;

determining one or more target languages relevant to the query using one or more language scores associated with each of the one or more query terms, wherein determining one or more target languages relevant to the query includes;

identifying terms related to the query;

for each related term, determining a language score for each of a plurality of languages;

combining the language scores for each related term for each respective language of the plurality of languages; and

determining one or more target languages relevant to the query, other than the source language, as corresponding to languages of the plurality of languages having a combined language score beyond a threshold score;

translating the query into one or more translated queries in the respective one or more target languages;

determining search results responsive to the respective one or more translated queries; and

providing one or more of the search results.

8. The system of claim 7, further operable to perform operations comprising:

combining the determined search results for the one or more queries into a single ordered list of search results.

9. The system of claim 7, where the providing includes translating the determined search results into the source language.

10. The system of claim 9, further operable to perform operations comprising:

selectively providing an original language search result for presentation corresponding to a provided translated search result, where the original language search result is provided for presentation below the translated search result, and where original language search results are provided independently according to user selection.

11. The system of claim 7, where identifying a language score for each related term includes identifying the related term in a table that maps a plurality of terms to corresponding pre-computed language scores.

12. The system of claim 7, wherein the related terms are terms that are likely to co-occur with one or more query terms.

13. A non-transitory computer storage medium encoded with a computer program, the program comprising instructions that when executed by data processing apparatus cause the data processing apparatus to perform operations comprising:

receiving a query in a source language, the query including one or more query terms;

determining one or more target languages relevant to the query using one or more language scores associated with each of the one or more query terms, wherein determining one or more target languages relevant to the query includes;

identifying terms related to the query;

for each related term, determining a language score for each of a plurality of languages;

combining the language scores for each related term for each respective language of the plurality of languages; and

determining one or more target languages relevant to the query, other than the source language, as corresponding to languages of the plurality of languages having a combined language score beyond a threshold score;

translating the query into one or more translated queries in the respective one or more target languages;

determining search results responsive to the respective one or more translated queries; and

providing one or more of the search results.

14. The computer storage medium of claim 13, further comprising instructions to perform operations comprising:

combining the determined search results for the one or more queries into a single ordered list of search results.

15. The computer storage medium of claim 13, where the providing includes translating the determined search results into the source language.

16. The computer storage medium of claim 15, further comprising instructions to perform operations comprising:

selectively providing an original language search result for presentation corresponding to a provided translated search result, where the original language search result is provided for presentation below the translated search result, and where original language search results are provided independently according to user selection.

17. The computer storage medium of claim 13, where identifying a language score for each related term includes identifying the related term in a table that maps a plurality of terms to corresponding pre-computed language scores.

18. The computer storage medium of claim 13, wherein the related terms are terms that are likely to co-occur with one or more query terms.