Quotation identification

• US 9,323,721 B1
• Filed: 02/27/2013
• Issued: 04/26/2016
• Est. Priority Date: 02/27/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Duddu, Sarveshwar, Banerjee, Avishek, Singh, Kartik
• Primary Examiner(s): Reinier, Barbara
• Application Number:
  US13/778,921
• Time in Patent Office: 1,154 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking

Abstract

Methods, and systems, including computer programs encoded on computer-readable storage mediums, including a method for identifying quotations occurring in resources. The method includes identifying first and second quotations that occur in particular resources in a set of resources, each particular resource being classified as a quotation-related resource; determining, for each of the first and second quotations, a number of occurrences of the quotation in the set and a number of different resources in the set in which the quotation occurs; determining that the first quotation and the second quotation are (i) semantically related and (ii) not identical; selecting a representative quotation from among the first quotation and the second quotation; and storing the representative quotation, the number of occurrences of the representative quotation and the number of different resources in which the representative quotation occurs in association with an entity to which the representative quotation is attributed.

Claims

1. A computer-implemented method comprising:

identifying first and second quotations that occur in particular resources in a set of resources, each of the particular resources being classified as a quotation-related resource;

determining, for each of the first and second quotations, a number of occurrences of the quotation in the set of resources and a number of different resources in the set of resources in which the quotation occurs;

determining that the first quotation and the second quotation are (i) semantically related and (ii) not identical;

selecting, by one or more data processors, a representative quotation from among the first quotation and the second quotation;

storing the representative quotation, the number of occurrences of the representative quotation, and the number of different resources in which the representative quotation occurs in association with an entity to which the representative quotation is attributed;

receiving a search query;

determining, based on one or more terms of the search query, that the search query references the entity;

in response to determining that the search query references the entity, determining, based on the stored number of occurrences of the representative quotation and the stored number of different resources in which the representative quotation occurs in association with the entity, to include a section that references information about the entity in a search result page that is responsive to the search query;

in response to determining to include the section that references information about the entity in the search result page that is responsive to the search query based on the stored number of occurrences of the representative quotation and the stored number of different resources in which the representative quotation occurs in association with the entity, selecting the representative quotation; and

providing, by a search engine to a user device, the search results page including the representative quotation in the section that includes information about the entity.

2. The method of claim 1, wherein selecting the representative quotation comprises:

comparing the number of occurrences of the first quotation in the set of resources to the number of occurrences of the second quotation in the set of resources; and

selecting the representative quotation based at least in part on the comparison.

3. The method of claim 1, wherein each of the first and second quotations is content delimited by quotation marks in the particular resources.

4. The method of claim 1, further comprising:

identifying a third quotation that occurs in particular resources; and

filtering and discarding the third quotation based on one or more filtering conditions specifying restrictions on content of the quotation.

5. The method of claim 4, wherein the restrictions comprise one or more of restrictions on numeric characters in the quotation, restrictions on the quotation commencing with lower case characters, restrictions on designated characters in the quotation, and restrictions on a number of capitalized terms in the quotation.

6. The method of claim 1, comprising discarding a one of the first and second quotations that is not the representative quotation.

7. The method of claim 1, comprising:

determining, for each of the first and second quotations, that the number of occurrences of the quotation in the set of resources exceeds a minimum occurrences threshold and that the number of different resources in the set of resources in which the quotation occurs exceeds a minimum different resources threshold.

8. The method of claim 1, wherein the set of resources includes resources that are not classified as quotation-related resources and the numbers of occurrences of the first and second quotations include occurrences in the resources that are not classified as quotation-related resources.

9. The method of claim 1, wherein determining whether to present the representative quotation in a search result page responsive to a search query that involves the entity based on the stored number of occurrences of the representative quotation and the stored number of different resources in which the representative quotation occurs in association with the entity, comprises:

receiving the search query;

determining that the search query includes one or more search terms associated with the entity;

in response to determining that the search query includes one or more search terms associated with the entity, accessing the stored representative quotation, the stored number of occurrences of the stored representative quotation, and the stored number of different resources in which the stored representative quotation occurs in association with the entity; and

determining whether to include the stored representative quotation in the search results page responsive to the search query based on the stored number of occurrences of the stored representative quotation and the stored number of different resources in which the stored representative quotation occurs.

10. The method of claim 1, wherein determining, based on one or more terms of the search query, that the search query references the entity comprises:

identifying one or more resources that are responsive to the search query;

determining whether a number of the one or more identified resources that include one or more quotations attributed to the entity satisfies a predetermined threshold; and

in response to determining that the number of the one or more identified resources that include one or more quotations attributed to the entity satisfies the predetermined threshold, determining that the search query references the entity.

11. A system comprising:

one or more data processors; and

instructions stored on a computer-readable storage apparatus that when executed by the one or more data processors cause the one or more data processors to perform operations comprising;

identifying first and second quotations that occur in particular resources in a set of resources, each of the particular resources being classified as a quotation-related resource;

determining, for each of the first and second quotations, a number of occurrences of the quotation in the set of resources and a number of different resources in the set of resources in which the quotation occurs;

determining that the first quotation and the second quotation are (i) semantically related and (ii) not identical;

selecting a representative quotation from among the first quotation and the second quotation;

receiving a search query;

determining, based on one or more terms of the search query, that the search query references the entity;

in response to determining that the search query references the entity, determining, based on the stored number of occurrences of the representative quotation and the stored number of different resources in which the representative quotation occurs in association with the entity, to include a section that references information about the entity in a search result page that is responsive to the search query;

in response to determining to include the section that references information about the entity in the search result page that is responsive to the search query based on the stored number of occurrences of the representative quotation and the stored number of different resources in which the representative quotation occurs in association with the entity, selecting the representative quotation; and

providing, by a search engine to a user device, the search results page including the representative quotation in the section that includes information about the entity.

12. The system of claim 11, wherein selecting the representative quotation comprises:

comparing the number of occurrences of the first quotation in the set of resources to the number of occurrences of the second quotation in the set of resources; and

selecting the representative quotation based at least in part on the comparison.

13. The system of claim 11, wherein each of the first and second quotations is content delimited by quotation marks in the particular resources.

14. The system of claim 11, wherein the instructions, when executed by the one or more data processors, cause the one or more data processors to perform operations comprising:

identifying a third quotation that occurs in particular resources; and

filtering and discarding the third quotation based on one or more filtering conditions specifying restrictions on content of the quotation.

15. The system of claim 14, wherein the restrictions comprise one or more of restrictions on numeric characters in the quotation, restrictions on the quotation commencing with lower case characters, restrictions on designated characters in the quotation, and restrictions on a number of capitalized terms in the quotation.

16. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

identifying first and second quotations that occur in particular resources in a set of resources, each of the particular resources being classified as a quotation-related resource;

determining, for each of the first and second quotations, a number of occurrences of the quotation in the set of resources and a number of different resources in the set of resources in which the quotation occurs;

determining that the first quotation and the second quotation are (i) semantically related and (ii) not identical;

selecting, by one or more data processors, a representative quotation from among the first quotation and the second quotation;

storing the representative quotation, the number of occurrences of the representative quotation, and the number of different resources in which the representative quotation occurs in association with an entity to which the representative quotation is attributed;

receiving a search query;

determining, based on one or more terms of the search query, that the search query references the entity;

in response to determining that the search query references the entity, determining, based on the stored number of occurrences of the representative quotation and the stored number of different resources in which the representative quotation occurs in association with the entity, to include a section that references information about the entity in a search result page that is responsive to the search query;

in response to determining to include the section that references information about the entity in the search result page that is responsive to the search query based on the stored number of occurrences of the representative quotation and the stored number of different resources in which the representative quotation occurs in association with the entity, selecting the representative quotation; and

providing, by a search engine to a user device, the search results page including the representative quotation in the section that includes information about the entity.

17. The medium of claim 16, wherein selecting the representative quotation comprises:

comparing the number of occurrences of the first quotation in the set of resources to the number of occurrences of the second quotation in the set of resources; and

selecting the representative quotation based at least in part on the comparison.

18. The medium of claim 16, wherein each of the first and second quotations is content delimited by quotation marks in the particular resources.

19. The medium of claim 16, the operations further comprising:

identifying a third quotation that occurs in particular resources; and

filtering and discarding the third quotation based on one or more filtering conditions specifying restrictions on content of the quotation.

20. The medium of claim 19, wherein the restrictions comprise one or more of restrictions on numeric characters in the quotation, restrictions on the quotation commencing with lower case characters, restrictions on designated characters in the quotation, and restrictions on a number of capitalized terms in the quotation.