Using web ranking to resolve anaphora

• US 9,542,441 B1
• Filed: 11/06/2015
• Issued: 01/10/2017
• Est. Priority Date: 03/14/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Paskin, Mark Andrew, Buchanan, Michael, Gupta, Pravir Kumar
• Primary Examiner(s): Pham, Hung Q
• Application Number:
  US14/935,268
• Time in Patent Office: 431 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24522 Translation of natural language queries to structured queries
• CPC Class Codes: G06F 16/2455 Query execution
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/3325 Reformulation based on results of preceding query
• CPC Class Codes: G06F 16/3334 Selection or weighting of terms from queries, including natural language queries
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques

Abstract

The specification relates to a method of receiving a first query and a second query. The method analyzes the second query for a presence of anaphora. If anaphora is present, the method analyzes the first query for a presence of an entity that can be associated with the anaphora. If the analysis analyzing the first query returns two or more associated entities, the method forms a third query wherein the anaphora of the second query is replaced with one of the associated entities and forms a fourth query wherein the anaphora is replaced with the other of the associated entities. The third query and the fourth query are sent to a query-ranking engine. The third query and the fourth query receive a ranking and the higher-ranked query is sent to a search engine.

Claims

1. A method comprising:

receiving a first query;

receiving a second, follow-up query;

determining that a pronoun in the second, follow-up query is an anaphor by determining that the pronoun refers to an entity that is not present in the second, follow-up query;

in response to determining that the pronoun in the second, follow-up query is an anaphor, determining that the first query is associated with a plurality of possible entities;

generating a plurality of candidate queries, wherein each candidate query of the plurality of candidate queries is generated by replacing the pronoun in the second, follow-up query with a corresponding possible entity;

ranking, using at least past query logs stored in a data repository, the plurality of candidate queries; and

providing a highest-ranked candidate query of the plurality of candidate queries to a search engine and obtaining search results for the highest-ranked candidate query from the search engine.

2. The method of claim 1, wherein the past query logs associate past queries with at least one of a popularity of the past queries, a frequency of use of the past queries, or a commonality of the past queries, and wherein ranking the plurality of candidate queries comprises ranking the candidate queries based on at least one of a popularity of the candidate queries, a frequency of use of the candidate queries, or a commonality of the candidate queries.

3. The method of claim 1, further comprising:

modifying one or more of the plurality of candidate queries before sending the plurality of candidate queries to the ranking engine.

4. The method of claim 3, wherein modifying one or more of the plurality of candidate queries comprises one or more of dropping search terms, replacing search terms with synonyms, or introducing new terms.

5. The method of claim 1, wherein determining that the first query is associated with a plurality of possible entities comprises:

analyzing results of the first query for a presence of an entity associated with the anaphor.

6. The method of claim 1, further comprising:

determining that the highest-ranked candidate query is ranked higher than the second, follow-up query; and

providing the highest-ranked candidate query to the search engine in response to determining that the highest-ranked candidate query is ranked higher than the second, follow-up query.

7. The method of claim 1, further comprising:

providing the search results for the highest-ranked candidate query for presentation to a user as part of a response to the second, follow-up query.

8. A system comprising one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to perform operations comprising:

receiving a first query;

receiving a second, follow-up query;

determining that a pronoun in the second, follow-up query is an anaphor by determining that the pronoun refers to an entity that is not present in the second, follow-up query;

in response to determining that the pronoun in the second, follow-up query is an anaphor, determining that the first query is associated with a plurality of possible entities;

generating a plurality of candidate queries, wherein each candidate query of the plurality of candidate queries is generated by replacing the pronoun in the second, follow-up query with a corresponding possible entity;

ranking, using at least past query logs stored in a data repository, the plurality of candidate queries; and

providing a highest-ranked candidate query of the plurality of candidate queries to a search engine and obtaining search results for the highest-ranked candidate query from the search engine.

9. The system of claim 8, wherein the past query logs associate past queries with at least one of a popularity of the past queries, a frequency of use of the past queries, or a commonality of the past queries, and wherein ranking the plurality of candidate queries comprises ranking the candidate queries based on at least one of a popularity of the candidate queries, a frequency of use of the candidate queries, or a commonality of the candidate queries.

10. The system of claim 8, the operations further comprising:

modifying one or more of the plurality of candidate queries before ranking the plurality of candidate queries.

11. The system of claim 10, wherein modifying one or more of the plurality of candidate queries comprises one or more of dropping search terms, replacing search terms with synonyms, or introducing new terms.

12. The system of claim 8, wherein determining that the first query is associated with a plurality of possible entities comprises:

analyzing results of the first query for a presence of an entity associated with the anaphor.

13. The system of claim 8, the operations further comprising:

determining that the highest-ranked candidate query is ranked higher than the second, follow-up query; and

providing the highest-ranked candidate query to the search engine in response to determining that the highest-ranked candidate query is ranked higher than the second, follow-up query.

14. The system of claim 8, the operations further comprising:

providing the search results for the highest-ranked candidate query for presentation to a user as part of a response to the second, follow-up query.

15. One or more non-transitory storage media encoded with a computer program, the computer program comprising instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:

receiving a first query;

receiving a second, follow-up query;

determining that a pronoun in the second, follow-up query is an anaphor by determining that the pronoun refers to an entity that is not present in the second, follow-up query;

in response to determining that the pronoun in the second, follow-up query is an anaphor, determining that the first query is associated with a plurality of possible entities;

generating a plurality of candidate queries, wherein each candidate query of the plurality of candidate queries is generated by replacing the pronoun in the second, follow-up query with a corresponding possible entity;

ranking, using at least past query logs stored in a data repository, the plurality of candidate queries; and

providing a highest-ranked candidate query of the plurality of candidate queries to a search engine and obtaining search results for the highest-ranked candidate query from the search engine.

16. The non-transitory storage media of claim 15, wherein the past query logs associate past queries with at least one of a popularity of the past queries, a frequency of use of the past queries, or a commonality of the past queries, and wherein ranking the plurality of candidate queries comprises ranking the candidate queries based on at least one of a popularity of the candidate queries, a frequency of use of the candidate queries, or a commonality of the candidate queries.

17. The non-transitory storage media of claim 15, the operations further comprising:

modifying one or more of the plurality of candidate queries before ranking the plurality of candidate queries.

18. The non-transitory storage media of claim 15, wherein determining that the first query is associated with a plurality of possible entities comprises:

analyzing results of the first query for a presence of an entity associated with the anaphor.

19. The non-transitory storage media of claim 15, the operations further comprising:

determining that the highest-ranked candidate query is ranked higher than the second, follow-up query; and

providing the highest-ranked candidate query to the search engine in response to determining that the highest-ranked candidate query is ranked higher than the second, follow-up query.

20. The non-transitory storage media of claim 15, the operations further comprising:

providing the search results for the highest-ranked candidate query for presentation to a user as part of a response to the second, follow-up query.