Corroborating facts in electronic documents

• US 8,954,412 B1
• Filed: 09/28/2006
• Issued: 02/10/2015
• Est. Priority Date: 09/28/2006
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Zhao, Shubin, Czuba, Krzysztof
• Primary Examiner(s): NGUYEN, KIM T
• Application Number:
  US11/536,504
• Time in Patent Office: 3,057 Days
• Field of Search: 707/706, 707/771
• US Class Current: 707/706
• CPC Class Codes: G06F 16/2365 Ensuring data consistency and integrity
• CPC Class Codes: G06F 16/2425 Iterative querying; Query formulation based on the results of a preceding query
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06N 5/041 Abduction

Abstract

A query is defined that has an answer formed of terms from electronic documents. A repository having facts is examined to identify attributes corresponding to terms in the query. The electronic documents are examined to find other terms that commonly appear near the query terms. Hypothetical facts representing possible answers to the query are created based on the information identified in the fact repository and the commonly-appearing terms. These hypothetical facts are corroborated using the electronic documents to determine how many documents support each fact. Additionally, contextual clues in the documents are examined to determine whether the hypothetical facts can be expanded to include additional terms. A hypothetical fact that is supported by at least a certain number of documents, and is not contained within another fact with at least the same level of support, is presented as likely correct.

Claims

1. A computer-implemented method for identifying facts described by electronic documents, comprising:

defining a query, the query posing a question having an answer formed of terms from the electronic documents;

creating one or more hypothetical facts in response to the query and the electronic documents, each hypothetical fact representing a possible answer to the query, wherein creating one or more hypothetical facts in response to the query comprises;

parsing the query to filter out noise words and produce filtered terms;

searching a repository of facts comprising attributes and values to identify attributes corresponding to the filtered terms;

searching the electronic documents to identify terms that frequently appear near the filtered terms; and

forming one or more hypothetical facts responsive to the attributes corresponding to the filtered terms and the terms that frequently appear near the filtered terms in the electronic documents;

corroborating the one or more hypothetical facts using the electronic documents to identify a likely correct fact; and

presenting the identified likely correct fact as the answer to the query.

2. The method of claim 1, wherein defining a query comprises:

receiving a real-time query from a user of a web site.

3. The method of claim 1, wherein defining a query comprises:

receiving a set of historical queries submitted by users of a web site; and

defining the query based on at least one of the historical queries in the set.

4. The method of claim 1, wherein corroborating a hypothetical fact using the electronic documents comprises:

determining how many of the electronic documents support the hypothetical fact;

identifying the hypothetical fact as likely correct if an amount of support for the hypothetical fact surpasses a threshold.

5. The method of claim 4, wherein identifying the hypothetical fact as likely correct comprises:

identifying the hypothetical fact as likely correct if it is not contained within another hypothetical fact having at least a same amount of support.

6. The method of claim 1, wherein a hypothetical fact comprises a value having one or more original terms and wherein corroborating a hypothetical fact using the electronic documents comprises:

identifying an electronic document that mentions the one or more original terms of the hypothetical fact;

examining contextual clues in the electronic document to determine whether the hypothetical fact can be expanded to include one or more additional terms; and

responsive to a positive determination that the hypothetical fact can be expanded, creating a new hypothetical fact having the original terms and the additional terms.

7. The method of claim 6, wherein the electronic document is described by a markup language having open and close tags and wherein examining contextual clues in the electronic document comprises:

identifying open and close tags surrounding the original terms in the electronic document; and

identifying additional terms within the open and close tags surrounding the original terms in the electronic document.

8. The method of claim 1, wherein presenting the identified likely correct fact as the answer to the query comprises:

displaying the likely correct fact on a web page.

9. The method of claim 1, wherein presenting the identified likely correct fact as the answer to the query comprises:

storing the likely correct fact in a fact repository.

10. A system for identifying facts described by electronic documents, comprising:

one or more processors;

memory; and

one or more programs stored in the memory, the one or more programs comprising instructions to;

define a query, the query posing a question having an answer formed of terms from the electronic documents;

create one or more hypothetical facts in response to the query and the electronic documents, each hypothetical fact representing a possible answer to the query, wherein creating one or more hypothetical facts in response to the query comprises;

parsing the query to filter out noise words and produce filtered terms;

searching a repository of facts comprising attributes and values to identify attributes corresponding to the filtered terms;

searching the electronic documents to identify terms that frequently appear near the filtered terms; and

forming one or more hypothetical facts responsive to the attributes corresponding to the filtered terms and the terms that frequently appear near the filtered terms in the electronic documents;

corroborate the one or more hypothetical facts using the electronic documents to identify a likely correct fact; and

present the identified likely correct fact as the answer to the query.

11. The system of claim 10, wherein the instructions to define the query include instructions to receive a real-time query from a user of a web site.

12. The system of claim 10, wherein the instructions to define the query include instructions to receive a set of historical queries submitted by users of a web site and define the query based on at least one of the historical queries in the set.

13. The system of claim 10, wherein the instructions to corroborate the one or more hypothetical facts include instructions to:

determine how many of the electronic documents support the hypothetical fact;

identify the hypothetical fact as likely correct if an amount of support for the hypothetical fact surpasses a threshold.

14. The system of claim 13, wherein the instructions to identify the hypothetical fact as likely correct include instructions to identify the hypothetical fact as likely correct if it is not contained within another hypothetical fact having at least a same amount of support.

15. The system of claim 10, wherein a hypothetical fact comprises a value having one or more original terms and wherein the instructions to corroborate the one or more hypothetical facts include instructions to:

identify an electronic document that mentions the one or more original terms of the hypothetical fact; and

examine contextual clues in the electronic document to determine whether the hypothetical fact can be expanded to include one or more additional terms, and, responsive to a positive determination that the hypothetical fact can be expanded, creating a new hypothetical fact having the original terms and the additional terms.

16. The system of claim 15, wherein the electronic document is described by a markup language having open and close tags and wherein the instructions to examine contextual clues in the electronic document include one or more additional terms include instructions to identify open and close tags surrounding the original terms in the electronic document, and identify additional terms within the open and close tags surrounding the original terms in the electronic document.

17. The system of claim 10, wherein the instructions to present the identified likely correct fact include instructions to display the likely correct fact on a web page.

18. The system of claim 10, wherein the instructions to present the identified likely correct fact include instructions to store the likely correct fact in a fact repository.

19. A non-transitory computer readable storage medium storing one or more programs configured for execution by a computer, the one or more programs comprising instructions for:

defining a query, the query posing a question having an answer formed of terms from the electronic documents;

creating one or more hypothetical facts in response to the query and the electronic documents, each hypothetical fact representing a possible answer to the query, wherein creating one or more hypothetical facts in response to the query comprises;

parsing the query to filter out noise words and produce filtered terms;

searching a repository of facts comprising attributes and values to identify attributes corresponding to the filtered terms;

searching the electronic documents to identify terms that frequently appear near the filtered terms; and

forming one or more hypothetical facts responsive to the attributes corresponding to the filtered terms and the terms that frequently appear near the filtered terms in the electronic documents;

corroborating the one or more hypothetical facts using the electronic documents to identify a likely correct fact; and

presenting the identified likely correct fact as the answer to the query.

20. The computer readable storage medium of claim 19, further comprising instructions for receiving a real-time query from a user of a web site.

21. The computer readable storage medium claim 19, further comprising instructions for receiving a set of historical queries submitted by users of a web site and defining the query based on at least one of the historical queries in the set.

22. The computer readable storage medium of claim 19, further comprising instructions for:

determining how many of the electronic documents support the hypothetical fact;

identifying the hypothetical fact as likely correct if an amount of support for the hypothetical fact surpasses a threshold.

23. The computer readable storage medium of claim 22, further comprising instructions for identifying the hypothetical fact as likely correct if it is not contained within another hypothetical fact having at least a same amount of support.

24. The computer readable storage medium of claim 19, wherein a hypothetical fact comprises a value having one or more original terms and wherein instructions for corroborating a hypothetical fact using the electronics documents further comprises instructions for:

identifying an electronic document that mentions the one or more original terms of the hypothetical fact; and

examining contextual clues in the electronic document to determine whether the hypothetical fact can be expanded to include one or more additional terms, and, responsive to a positive determination that the hypothetical fact can be expanded, creating a new hypothetical fact having the original terms and the additional terms.

25. The computer readable storage medium of claim 24, wherein the electronic document is described by a markup language having open and close tags and wherein the fact expansion module is adapted to identify open and close tags surrounding the original terms in the electronic document, and identify additional terms within the open and close tags surrounding the original terms in the electronic document.

26. The computer readable storage medium of claim 19, further comprising instructions for displating the likely correct fact on a web page.

27. The computer readable storage medium of claim 19, further comprising instructions for storing the likely correct fact in a fact repository.