Cross-lingual indexing and information retrieval

• US 8,594,994 B1
• Filed: 12/12/2011
• Issued: 11/26/2013
• Est. Priority Date: 08/21/2003
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Dean, Jeffrey A.
• Primary Examiner(s): Shah, Paras D
• Application Number:
  US13/323,034
• Time in Patent Office: 715 Days
• Field of Search: 704/2, 704/4, 704/5, 704/8, 704/6, 704/7, 704/9, 704/10, 707/705, 707/706, 707/708
• US Class Current: 704/7
• CPC Class Codes: G06F 16/243 Natural language query formulation
• CPC Class Codes: G06F 40/49 using very large corpora, e.g. the web
• 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

Systems and methods are disclosed for searching across multi-lingual information. A user makes a query in a first language, and a group of documents that were previously machine-translated into the first language are searched for information responsive to the query. Contextual information derived can be used to improve the accuracy of the machine translation. Responsive documents are returned to the user. Alternatively, a query provided in a user'"'"'s language may be translated into one or more other languages. Documents written in these languages can then be searched for information responsive to the appropriate translated query. Responsive documents can be translated into the user'"'"'s language prior to providing them to the user.

Claims

1. A method implemented by one or more computers, the method comprising:

translating anchor text of a collection of documents to a target language using a context-specific translation model, wherein one or more of the documents in the collection of documents include anchor text for links that point to one or more documents outside of the collection of documents, wherein the one or more documents outside the collection of documents are in the target language, and wherein anchor text in the one or more of the documents in the collection of documents is translated by the context-specific translation model using, at least in part, the one or more documents outside of the collection of documents that are linked to the respective anchor text;

indexing the translated anchor text to create one or more anchor text indexes;

indexing the one or more of the documents outside of the collection of documents that are in the target language to create one or more document indexes; and

providing the anchor text indexes and the document indexes for use in responding to queries.

2. The method of claim 1, further comprising:

obtaining a new document to be indexed;

translating the new document into the target language; and

indexing the translated document in one or more of the document indexes.

3. The method of claim 1, further comprising:

obtaining a new document to be indexed;

translating anchor text of the new document to the target language; and

indexing the translated anchor text of the new document in one or more of the anchor text indexes.

4. The method of claim 1, further comprising:

receiving a query in a first language;

translating the query into the target language to form a first translated query;

identifying one or more documents that are responsive to the first translated query using the anchor text indexes and document indexes; and

providing a response to the first translated query based on the identified documents.

5. The method of claim 4 wherein identifying one or more documents that are responsive to the first translated query using the anchor text indexes and document indexes and providing a response to the first translated query based on the identified documents comprises:

identifying anchor text in the target language that is responsive to the first translated query, wherein the anchor text links to one or more documents that are in the target language; and

providing the one or more documents that are in the target language in response to the first translated query.

6. The method of claim 4 wherein providing a response to the first translated query comprises:

determining that an identified document containing information responsive to the first translated query is not written in the first language; and

in response to the determination, translating the given document to the first language.

7. The method of claim 1 wherein the documents in the collection of documents include web pages and offline documents.

8. A system comprising:

one or more computers programmed to perform operations comprising;

translating anchor text of a collection of documents to a target language using a context-specific translation model, wherein one or more of the documents in the collection of documents include anchor text for links that point to one or more documents outside of the collection of documents, wherein the one or more documents outside the collection of documents are in the target language, and wherein anchor text in the one or more of the documents in the collection of documents is translated by the context-specific translation model using, at least in part, the one or more documents outside of the collection of documents that are linked to the respective anchor text;

indexing the translated anchor text to create one or more anchor text indexes;

indexing the one or more of the documents outside of the collection of documents that are in the target language to create one or more document indexes; and

providing the anchor text indexes and the document indexes for use in responding to queries.

9. The system of claim 8 wherein the operations further comprise:

obtaining a new document to be indexed;

translating the new document into the target language; and

indexing the translated document in one or more of the document indexes.

10. The system of claim 8 wherein the operations further comprise:

obtaining a new document to be indexed;

translating anchor text of the new document to the target language; and

indexing the translated anchor text of the new document in one or more of the anchor text indexes.

11. The system of claim 8 wherein the operations further comprise:

receiving a query in a first language;

translating the query into the target language to form a first translated query;

identifying one or more documents that are responsive to the first translated query using the anchor text indexes and document indexes; and

providing a response to the first translated query based on the identified documents.

12. The system of claim 11 wherein identifying one or more documents that are responsive to the first translated query using the anchor text indexes and document indexes and providing a response to the first translated query based on the identified documents comprises:

identifying anchor text in the target language that is responsive to the first translated query, wherein the anchor text links to one or more documents that are in the target language; and

providing the one or more documents that are in the target language in response to the first translated query.

13. The system of claim 11 wherein providing a response to the first translated query comprises:

determining that an identified document containing information responsive to the first translated query is not written in the first language; and

in response to the determination, translating the given document to the first language.

14. The system of claim 8 wherein the documents in the collection of documents include web pages and offline documents.

15. A non-transitory computer readable media encoded with instructions that are operable, when executed by a computer, to cause the computer to perform operations comprising:

translating anchor text of a collection of documents to a target language using a context-specific translation model, wherein one or more of the documents in the collection of documents include anchor text for links that point to one or more documents outside of the collection of documents, wherein the one or more documents outside the collection of documents are in the target language, and wherein anchor text in the one or more of the documents in the collection of documents is translated by the context-specific translation model using, at least in part, the one or more documents outside of the collection of documents that are linked to the respective anchor text;

indexing the translated anchor text to create one or more anchor text indexes;

indexing the one or more of the documents outside of the collection of documents that are in the target language to create one or more document indexes; and

providing the anchor text indexes and the document indexes for use in responding to queries.

16. The computer readable media of claim 15 wherein the operations further comprise:

obtaining a new document to be indexed;

translating the new document into the target language; and

indexing the translated document in one or more of the document indexes.

17. The computer readable media of claim 15 wherein the operations further comprise:

obtaining a new document to be indexed;

translating anchor text of the new document to the target language; and

indexing the translated anchor text of the new document in one or more of the anchor text indexes.

18. The computer readable media of claim 15 wherein the operations further comprise:

receiving a query in a first language;

translating the query into the target language to form a first translated query;

identifying one or more documents that are responsive to the first translated query using the anchor text indexes and document indexes; and

providing a response to the first translated query based on the identified documents.

19. The computer readable media of claim 18, wherein identifying one or more documents that are responsive to the first translated query using the anchor text indexes and document indexes and providing a response to the first translated query based on the identified documents comprises:

identifying anchor text in the target language that is responsive to the first translated query, wherein the anchor text links to one or more documents that are in the target language; and

providing the one or more documents that are in the target language in response to the first translated query.

20. The computer readable media of claim 18, wherein providing a response to the first translated query comprises:

determining that an identified document containing information responsive to the first translated query is not written in the first language; and

in response to the determination, translating the given document to the first language.

21. The computer readable media of claim 15, wherein the documents in the collection of documents include web pages and offline documents.