Coreference resolution in an ambiguity-sensitive natural language processing system

• US 8,712,758 B2
• Filed: 08/29/2008
• Issued: 04/29/2014
• Est. Priority Date: 08/31/2007
• Status: Active Grant

• Current Assignee: Zhigu Holdings Limited
• Original Assignee: Microsoft Corporation
• Inventors: Crouch, Richard, Van den Berg, Martin Henk, Salvetti, Franco, Thione, Giovanni Lorenzo, Ahn, David
• Primary Examiner(s): Dorvil, Richemond
• Assistant Examiner(s): ADESANYA, OLUJIMI A
• Application Number:
  US12/200,962
• Publication Number:
  US 20090076799A1
• Time in Patent Office: 2,069 Days
• Field of Search: 704/9
• US Class Current: 704/9
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

Technologies are described herein for coreference resolution in an ambiguity-sensitive natural language processing system. Techniques for integrating reference resolution functionality into a natural language processing system can processes documents to be indexed within an information search and retrieval system. Ambiguity awareness features, as well as ambiguity resolution functionality, can operate in coordination with coreference resolution. Annotation of coreference entities, as well as ambiguous interpretations, can be supported by in-line markup within text content or by external entity maps. Information expressed within documents can be formally organized in terms of facts, or relationships between entities in the text. Expansion can support applying multiple aliases, or ambiguities, to an entity being indexed so that all of the possibly references or interpretations for that entity are captured into the index. Alternative stored descriptions can support retrieval of a fact by either the original description or a coreferential description.

Claims

1. A method for integrating coreference resolution mechanisms, the method comprising:

retrieving, using a natural language engine of a server computer, a portion of text;

identifying, using the natural language engine of the server computer, a coreference within the portion of text;

extracting, using the natural language engine of the server computer, a fact from the portion of text, the fact having a meaning;

identifying an ambiguity within the portion of the text; and

expanding, using the natural language engine of the server computer, the fact to an expanded fact comprising

a coreferent meaning other than the meaning and based upon the identified coreference, and

an ambiguous meaning based on the identified ambiguity.

2. The method of claim 1, wherein identifying the coreference within the portion of text comprises identifying the coreference within the portion of text utilizing, at least in part, a syntactic parsing.

3. The method of claim 1, wherein identifying the coreference within the portion of text comprises identifying the coreference within the portion of text utilizing, at least in part, a semantic mapping.

4. The method of claim 1, wherein identifying the coreference comprises identifying an ambiguous coreference.

5. The method of claim 1, further comprising storing the expanded fact into an index operable to support information retrieval.

6. The method of claim 5, further comprising retrieving the expanded fact from the index in response to a search query.

7. The method of claim 1, further comprising annotating identified coreferences within the portion of text.

8. The method of claim 2, further comprising caching information from the syntactic parsing.

9. An optical disk storage device, magnetic disk storage device, or solid state storage device having computer executable instructions stored thereon which, when executed by a computer, cause the computer to:

retrieve a portion of text;

identify a coreference within the portion of text;

extract a fact from the portion of text, the fact having a meaning;

identifying an ambiguity within the portion of the text, and

expand the fact to comprise

a coreferent meaning other than the meaning and based upon the identified coreference, and

an ambiguous meaning based on the identified ambiguity.

10. The optical disk storage device, magnetic disk storage device, or solid state storage device of claim 9, wherein the instructions to identify the coreference comprise instructions to identify the coreference within the portion of text utilizing, at least in part, a syntactic parsing.

11. The optical disk storage device, magnetic disk storage device, or solid state storage device of claim 9, wherein the instructions to identify the coreference comprise instructions to identify the coreference within the portion of text utilizing, at least in part, a semantic mapping.

12. The optical disk storage device, magnetic disk storage device, or solid state storage device of claim 9, wherein the instructions to identify the coreference comprise instructions to identify an ambiguous coreference.

13. The optical disk storage device, magnetic disk storage device, or solid state storage device of claim 9, having further computer executable instructions stored thereon which, when executed by the computer, cause the computer to store the expanded fact into an index operable to support information retrieval.

14. The optical disk storage device, magnetic disk storage device, or solid state storage device of claim 13, having further computer executable instructions stored thereon which, when executed by the computer, cause the computer to retrieve the expanded fact from the index in response to a search query.

15. The optical disk storage device, magnetic disk storage device, or solid state storage device of claim 9, having further computer executable instructions stored thereon which, when executed by the computer, cause the computer to annotate identified coreferences within the portion of text.

16. A method for integrating coreference resolution mechanisms, the method comprising:

retrieving, using a natural language engine of a server computer, a portion of text;

identifying, using the natural language engine of the server computer, a coreference within the portion of text;

identifying, using the natural language engine of the server computer, an ambiguity within the portion of text;

extracting, using the natural language engine of the server computer, a fact from the portion of text, the fact having a meaning;

expanding, using the natural language engine of the server computer, the fact to comprise

a coreferent meaning other than the meaning and based upon the identified coreference, and

an ambiguous meaning based on the identified ambiguity;

storing the expanded fact into an index operable to support information retrieval; and

retrieving the expanded fact from the index in response to a search query.