FACT-BASED INDEXING FOR NATURAL LANGUAGE SEARCH

• US 20090063550A1
• Filed: 08/29/2008
• Published: 03/05/2009
• Est. Priority Date: 08/31/2007
• Status: Active Grant

• Current Assignee: Zhigu Holdings Limited
• Original Assignee: Powerset (Microsoft Corporation)
• Inventors: WATERS, CHAD, BOBROW, DANIEL, CHESLOW, ROBERT D., PELL, BARNEY D., THIONE, GIOVANNI LORENZO, VAN DEN BERG, MARTIN HENK
• Granted Patent: US 8,639,708 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/338 Presentation of query results

Abstract

Computer-readable media and a computer system for implementing a natural language search using fact-based structures and for generating such fact-based structures are provided. A fact-based structure is generated using a semantic structure, which represents information, such as text, from a document, such as a web page. Typically, a natural language parser is used to create a semantic structure of the information, and the parser identifies terms, as well as the relationship between the terms. A fact-based structure of a semantic structure allows for a linear structure of these terms and their relationships to be created, while also maintaining identifiers of the terms to convey the dependency of one fact-based structure on another fact-based structure. Additionally, synonyms and hypernyms are identified while generating the fact-based structure to improve the accuracy of the overall search.

Claims

1. One or more computer-readable media having computer-executable instructions embodied thereon that, when executed, perform a method for generating a fact-based index system for a natural language search, the method comprising:

generating one or more semantic structures using information from documents, wherein the information includes textual content, each semantic structure including at least one fact;

determining the at least one fact within the one or more semantic structures; and

generating one or more fact-based structures associated with each semantic structure, wherein each fact-based structure includes only one fact determined within the semantic structure.

2. The one or more computer-readable media of claim 1, wherein the one or more semantic structures include terms from the textual content and the relationship between the terms.

3. The one or more computer-readable media of claim 2, wherein the terms are represented by nodes in the one or more fact-based structures.

4. The one or more computer-readable media of claim 3, wherein the term is expanded to include synonyms or hypernyms represented by a node.

5. The one or more computer-readable media of claim 3, wherein the method further comprises assigning an identifier to each node.

6. The one or more computer-readable media of claim 1, wherein the information associated with a fact-based structure is retrieved when a user input in a search query matches the fact-based structure.

7. One or more computer-readable media having computer-executable instructions embodied thereon that, when executed, perform a method for implementing a natural language search using a fact-based index system, the method comprising:

generating one or more semantic structures using information from documents, wherein the information includes terms, each semantic structure including at least one fact;

determining the at least one fact within the one or more semantic structures;

generating one or more fact-based structures associated with each semantic structure, wherein each fact-based structure includes only one fact determined within the semantic structure; and

assigning an identifier for each term.

8. The one or more computer-readable media of claim 7, wherein the one or more semantic structures include terms from the textual content and the relationship between the terms.

9. The one or more computer-readable media of claim 8, wherein the terms are represented by nodes in the one or more fact-based structures.

10. The one or more computer-readable media of claim 9, wherein the relationship between terms is represented by edges connecting the nodes.

11. The one or more computer-readable media of claim 7, wherein we identify one or more facts, and we identify in the facts a first term and a second term, and the first term and the second term are defined as the same entity, and wherein both terms are assigned the same identifier.

12. The one or more computer-readable media of claim 7, wherein the documents include web pages.

13. The one or more computer-readable media of claim 7, wherein the method further comprises identifying matches between a user'"'"'s search input query and the fact-based structures.

14. The one or more computer-readable media of claim 13, wherein the method further comprises retrieving the matched fact-based structures.

15. A computer system embodied on one or more computer storage-media having computer-executable instructions provided thereon for performing a method for generating a fact-based structure, the system comprising:

a server that invokes a semantic index procedure configured for generating a fact-based structure, wherein the procedure is implemented on, at least, the following components;

(a) a fact-based structure generating component for generating a fact-based structure using a semantic structure associated with information from documents, the documents containing terms, wherein the semantic structure contains one or more facts; and

(b) an identifying component for identifying and assigning a identifier to each term.

16. The computer system of claim 15, further comprising a receiving component to receive a search input query from a user.

17. The computer system of claim 16, further comprising a matching component to match the search input query to the fact-based structure.

18. The computer system of claim 17, wherein the information associated with the matching fact-based structure is retrieved.

19. The computer system of claim 18, further comprising a presentation device for presenting the retrieved information.

20. The computer system of claim 15, wherein each term is expanded to include synonyms or hypernyms represented by a node.