Fact verification system

• US 20040122846A1
• Filed: 12/19/2002
• Published: 06/24/2004
• Est. Priority Date: 12/19/2002
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Krasikov, Sophia, Morar, John F., Segal, Alla, Chess, David M.
• Application Number:
  US10/324,723
• Publication Number:
  US 20040122846A1
• Time in Patent Office: Days
• US Class Current: 707/102
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 40/205 Parsing

Abstract

A system for providing fact verification for a body of text. The system includes either or both of: a fact-identification arrangement which automatically identifies at least one subset of the body of text potentially containing a fact-based statement; and a fact-verification arrangement which is adapted to automatically consult at least one information source towards determining whether at least one fact contained in a fact-based statement is true or false.

Claims

1. A system for providing fact verification for a body of text, said system comprising at least one of:

a fact-identification arrangement which automatically identifies at least one subset of the body of text potentially containing a fact-based statement; and

a fact-verification arrangement which is adapted to automatically consult at least one information source towards determining whether at least one fact contained in a fact-based statement is true or false.

2. The system according to claim 1, wherein said system comprises both of:

said fact-identification arrangement and said fact-verification arrangement.

3. The system according to claim 2, further comprising a result-presentation arrangement which presents results from at least one of said fact-identification and said fact-verification arrangements.

4. The system according to claim 2, wherein where said fact-verification component is adapted to automatically consult information on the World Wide Web.

5. The system according to claim 2, further comprising an arrangement for customizing a target list of sources to be consulted by said fact-verification arrangement.

6. The system according to claim 5, wherein said customizing arrangement is adapted to customize a target list of sources via the inclusion of at least one database comprising at least one of:

topical facts, known false statements, and commonly used facts.

7. The system according to claim 2, wherein said fact-identification arrangement is adapted to employ at least one predetermined component of the body of text towards identifying candidate facts.

8. The system according to claim 7, wherein the at least one predetermined component includes at least one of:

proper names, dates, weekday names, subject-specific keywords, names of diseases, quotations, titles, addresses, zip codes, telephone numbers, and geographical names.

9. The system according to claim 3, wherein said result-presentation arrangement is adapted to provide a list of results which includes at least one of:

statements of fact that were verified to be true, statements of fact that were found to be false, statements of fact whose truth could not be determined, and an indication of any subset of text that potentially included at least one statement of fact but which could not be adequately processed.

10. A method for deploying computing infrastructure, comprising integrating computer readable code into a computing system, wherein the code in combination with the computing system is capable of performing a method of providing fact verification for a body of text, comprising at least one of the following:

automatically identifying at least one subset of the body of text potentially containing a fact-based statement; and

automatically consulting at least one information source towards determining whether at least one fact contained in a fact-based statement is true or false.

11. The method according to claim 10, wherein said method comprises both of said identifying and consulting steps.

12. The method according to claim 11, further comprising the step of presenting results from at least one of said identifying and consulting steps.

13. The method according to claim 11, wherein where said consulting step comprises automatically consulting information on the World Wide Web.

14. The method according to claim 11, further comprising the step of customizing a target list of sources to be consulted in said consulting step.

15. The method according to claim 14, wherein said customizing step comprises customizing a target list of sources via the inclusion of at least one database comprising at least one of:

topical facts, known false statements, and commonly used facts.

16. The method according to claim 11, wherein said identifying step comprises employing at least one predetermined component of the body of text towards identifying candidate facts.

17. The method according to claim 16, wherein the at least one predetermined component includes at least one of:

proper names, dates, weekday names, subject-specific keywords, names of diseases, quotations, titles, addresses, zip codes, telephone numbers, and geographical names.

18. The method according to claim 12, wherein said step of presenting results comprises providing a list of results which includes at least one of:

statements of fact that were verified to be true, statements of fact that were found to be false, statements of fact whose truth could not be determined, and an indication of any subset of text that potentially included at least one statement of fact but which could not be adequately processed.

19. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for providing fact verification for a body of text, said method comprising at least one of the following steps:

automatically identifying at least one subset of the body of text potentially containing a fact-based statement; and

automatically consulting at least one information source towards determining whether at least one fact contained in a fact-based statement is true or false.