Apply corrections to an ingested corpus

• US 9,928,269 B2
• Filed: 01/03/2015
• Issued: 03/27/2018
• Est. Priority Date: 01/03/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bradley, Lisa M., Carlson, Christina R., Freed, Andrew R., Henderson, Roderick C.
• Primary Examiner(s): Lee, Wilson
• Application Number:
  US14/588,908
• Publication Number:
  US 20160196298A1
• Time in Patent Office: 1,179 Days
• Field of Search: None
• CPC Class Codes: G06F 16/2358 Change logging, detection, and notification replication G06F16/27
• CPC Class Codes: G06F 16/2379 Updates performed during online database operations; commit processing
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

An approach is provided to correct documents ingested by a question answering (QA) system. A document previously ingested by the QA system is selected. A correction to the selected document is identified from one or more correction sources and the correction is applied to the selected document within the QA system. In one embodiment, the correction source is a non-ingested document, such as a published document or an issued correction. In another embodiment, the correction source is a post in a forum. In this embodiment, a statement in the ingested document is compared with a contradictory statement found in an ingested post of a threaded discussion. The statement and the contradictory statement are evaluated by the QA system. The statement in the ingested document is replaced with the contradictory statement in response to the evaluation revealing that the contradictory statement is correct and that the statement is incorrect.

Claims

1. A method implemented by an information handling system that includes a memory and a processor, the method comprising:

selecting a document that has been ingested by a question answering (QA) system;

identifying a correction to the selected document from one or more correction sources, wherein the identifying comprises;

identifying a possible correction by comparing a first statement in the selected document with a second statement from a correction source, wherein the first and second statements each pertain to a same lexical answer type (LAT) and focus;

evaluating, by the QA system, the first statement and the second statement; and

determining that the second statement is more correct than the first statement in response to the evaluation; and

applying the correction to the selected document within the QA system by replacing the first statement with the second statement, wherein the selected document is part of a knowledge base utilized by the QA system to answer questions.

2. The method of claim 1 further comprising:

identifying a term in a first passage of the selected document;

detecting that an anaphor in a subsequent passage of the selected document references the identified term; and

resolving the anaphor found in the subsequent passage with the identified term.

3. The method of claim 2 wherein the identified term relates to the identified correction.

4. The method of claim 2 further comprising:

identifying a term in a first passage of the correction source;

detecting that an anaphor in a subsequent passage of the correction source references the identified term; and

resolving the anaphor found in the subsequent passage with the identified term.

5. The method of claim 1 wherein the correction source is selected from the group consisting of a forum post, a new document, and an issued correction.

6. The method of claim 1 further comprising:

archiving an original copy of the selected document prior to applying the correction; and

recording the correction source in a metadata associated with the ingested document.

7. An information handling system comprising:

one or more processors;

one or more data stores accessible by at least one of the processors;

a memory coupled to at least one of the processors; and

a set of computer program instructions stored in the memory and executed by at least one of the processors in order to perform actions of;

selecting a document that has been ingested by a question answering (QA) system;

identifying a correction to the selected document from one or more correction sources, wherein the identifying comprises;

identifying a possible correction by comparing a first statement in the selected document with a second statement from a correction source, wherein the first and second statements each pertain to a same lexical answer type (LAT) and focus;

evaluating, by the QA system, the first statement and the second statement; and

determining that the second statement is more correct than the first statement in response to the evaluation; and

applying the correction to the selected document within the QA system by replacing the first statement with the second statement, wherein the selected document is part of a knowledge base utilized by the QA system to answer questions.

8. The information handling system of claim 7 wherein the actions further comprise:

identifying a term in a first passage of the selected document;

detecting that an anaphor in a subsequent passage of the selected document references the identified term; and

resolving the anaphor found in the subsequent passage with the identified term.

9. The information handling system of claim 8 wherein the identified term relates to the identified correction.

10. The information handling system of claim 8 wherein the actions further comprise:

identifying a term in a first passage of the correction source;

detecting that an anaphor in a subsequent passage of the correction source references the identified term; and

resolving the anaphor found in the subsequent passage with the identified term.

11. The information handling system of claim 7 wherein the correction source is selected from the group consisting of a forum post, a new document, and an issued correction.

12. The information handling system of claim 7 wherein the actions further comprise:

archiving an original copy of the selected document prior to applying the correction; and

recording the correction source in a metadata associated with the ingested document.

13. A computer program product stored in a computer readable storage medium, comprising computer program code that, when executed by an information handling system, causes the information handling system to perform actions comprising:

selecting a document that has been ingested by a question answering (QA) system;

identifying a correction to the selected document from one or more correction sources, wherein the identifying comprises;

identifying a possible correction by comparing a first statement in the selected document with a second statement from a correction source, wherein the first and second statements each pertain to a same lexical answer type (LAT) and focus;

evaluating, by the QA system, the first statement and the second statement; and

determining that the second statement is more correct than the first statement in response to the evaluation; and

applying the correction to the selected document within the QA system by replacing the first statement with the second statement, wherein the selected document is part of a knowledge base utilized by the QA system to answer questions.

14. The computer program product of claim 13 wherein the actions further comprise:

identifying a term in a first passage of the selected document;

detecting that an anaphor in a subsequent passage of the selected document references the identified term; and

resolving the anaphor found in the subsequent passage with the identified term.

15. The computer program product of claim 14 wherein the identified term relates to the identified correction.

16. The computer program product of claim 14 wherein the actions further comprise:

identifying a term in a first passage of the correction source;

detecting that an anaphor in a subsequent passage of the correction source references the identified term; and

resolving the anaphor found in the subsequent passage with the identified term.

17. The computer program product of claim 13 wherein the correction source is selected from the group consisting of a forum post, a new document, and an issued correction.

18. The computer program product of claim 13, wherein the actions further comprise:

archiving an original copy of the selected document prior to applying the correction; and

recording the correction source in a metadata associated with the ingested document.