SYSTEM FOR AUTOMATICALLY GENERATING QUERIES

• US 20080005651A1
• Filed: 09/10/2007
• Published: 01/03/2008
• Est. Priority Date: 08/13/2001
• Status: Active Grant

• Current Assignee: III Holdings 6, LLC
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Shanahan, James, Grefenstette, Gregory
• Granted Patent: US 7,769,757 B2
• Time in Patent Office: Days
• US Class Current: 715/234
• CPC Class Codes: G06F 16/30 of unstructured textual data document management systems G06F16/93
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

A method, system and article of manufacture therefor, are disclosed for automatically generating a query from document content.

Claims

1. A method for automatically generating a query from selected document content, comprising:

identifying a set of entities in the selected document content for searching additional information related thereto using an information retrieval system;

analyzing the selected document content to extract one or more facets of document content;

producing an aspect vector with one or more of the extracted facets that surround the set of entities in the selected document content;

formulating the query by augmenting the set of entities with facets in the aspect vector to contextualize a search at the information retrieval system for information concerning the set of entities.

2. The method according to claim 1, wherein the number of extracted facets used to produce the aspect vector is limited to a predefined number of facets.

3. The method according to claim 1, further comprising identifying the set of entities using a service that recognizes entities of a predefined type.

4. The method according to claim 1, wherein the one or more facets of document content include proper names that are identified in the selected document content.

5. The method according to claim 1, wherein the one or more facets of document content include phrases that are identified in the selected document content.

6. The method according to claim 1, wherein the one or more facets of document content include rare phrases, which appear below a defined frequency in a reference corpus, that are identified in the selected document content.

7. The method according to claim 1, wherein the one or more facets of document content include dates that are identified in the selected document content.

8. The method according to claim 1, wherein the one or more facets of document content include numbers that are identified in the selected document content.

9. The method according to claim 1, wherein the one or more facets of document content include geographic locations that are identified in the selected document content.

10. The method according to claim 1, wherein the one or more facets of document content include rare words, which appear below a defined frequency in a reference corpus, that are identified in the selected document content.

15. The system according to claim 1, wherein the one or more facets of document content include phrases that are identified in the selected document content.

11. A system for automatically generating a query from selected document content, comprising:

an entity extractor for identifying a set of entities in the selected document content for searching additional information related thereto using an information retrieval system;

an aspect vector generator for (i) analyzing the selected document content to extract one or more facets of document content, and (ii) producing an aspect vector with one or more of the extracted facets that surround the set of entities in the selected document content;

a query generator for formulating the query by augmenting the set of entities with facets in the aspect vector to contextualize a search at the information retrieval system for information concerning the set of entities.

12. The system according to claim 11, wherein the number of extracted facets used to produce the aspect vector is limited to a predefined number of facets.

13. The system according to claim 11, wherein said entity extractor identifies the set of entities using a service that recognizes entities of a predefined type.

14. The system according to claim 11, wherein the one or more facets of document content include proper names that are identified in the selected document content.

16. The system according to claim 11, wherein the one or more facets of document content include rare phrases, which appear below a defined frequency in a reference corpus, that are identified in the selected document content.

17. The system according to claim 11, wherein the one or more facets of document content include dates that are identified in the selected document content.

18. The system according to claim 11, wherein the one or more facets of document content include numbers that are identified in the selected document content.

19. The system according to claim 11, wherein the one or more facets of document content include geographic locations that are identified in the selected document content.

20. The system according to claim 11, wherein the one or more facets of document content include rare words, which appear below a defined frequency in a reference corpus, that are identified in the selected document content.