Evidence diffusion among candidate answers during question answering

• US 8,738,365 B2
• Filed: 09/14/2012
• Issued: 05/27/2014
• Est. Priority Date: 09/28/2010
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Ferrucci, David A., Gondek, David C., Kalyanpur, Aditya A., Lally, Adam P.
• Primary Examiner(s): He, Jialong
• Application Number:
  US13/616,924
• Publication Number:
  US 20130018652A1
• Time in Patent Office: 620 Days
• Field of Search: 704/723, 704/9, 707/802
• US Class Current: 704/9
• CPC Class Codes: G06F 16/24564 Applying rules; Deductive queries
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems

Abstract

Diffusing evidence among candidate answers during question answering may identify a relationship between a first candidate answer and a second candidate answer, wherein the candidate answers are generated by a question-answering computer process, the candidate answers have associated supporting evidence, and the candidate answers have associated confidence scores. All or some of the evidence may be transferred from the first candidate answer to the second candidate answer based on the identified relationship. A new confidence score may be computed for the second candidate answer based on the transferred evidence.

Claims

1. A computer readable storage device storing a program of instructions executable by a machine to perform a method of diffusing evidence among candidate answers during question answering, comprising:

identifying, by a processor, a relationship between a first candidate answer and a second candidate answer, wherein the candidate answers are generated by a question-answering computer process for answering a question, the candidate answers have associated supporting evidence, and the candidate answers have associated confidence scores;

determining whether to transfer the associated supporting evidence from the first candidate answer to the second candidate answer, or to transfer the associated supporting evidence from the second candidate answer to the first candidate answer, by analyzing how the question is posed and types of the first candidate answer and the second candidate answer;

in response to determining to transfer the associated supporting evidence from the first candidate answer to the second candidate answer,

transferring all or some of the evidence from the first candidate answer to the second candidate answer based on the identified relationship, and

computing a new confidence score for the second candidate answer based on the transferred evidence and second candidate answer'"'"'s existing evidence;

in response to determining to transfer the associated supporting evidence from the second candidate answer to the first candidate answer,

transferring all or some of the evidence from the second candidate answer to the first candidate answer based on the identified relationship, and computing a new confidence score for the first candidate answer based on the transferred evidence and first candidate answer'"'"'s existing evidence.

2. The computer readable storage device of claim 1, wherein the transferring includes merging the transferred evidence with existing evidence information associated with the second candidate answer.

3. The computer readable storage medium of claim 1, wherein the transferring includes adding new evidence information denoting direction or strength, or both direction and strength, of the identified relationship.

4. The computer readable storage medium of claim 1, wherein the transferring includes transferring feature scores across candidates.

5. The computer readable storage medium of claim 1, wherein transferring further includes determining based on heuristics whether to transfer entire feature score as-is, or a fraction of the feature score based on type and strength of the identified one or more relationships.

6. The computer readable storage medium of claim 1, wherein the computing step is performed by machine learning.

7. The computer readable storage medium of claim 1, wherein the identifying includes consulting a structured knowledge base and mapping strings appearing in the candidate answers.

8. The computer readable storage device of claim 1, wherein the identifying step is based on lexical knowledge extracted from unstructured text.

9. A system for diffusing evidence among candidate answers during question answering, comprising:

a processor; and

an evidence diffusion module operable to identify a relationship between a first candidate answer and a second candidate answer, wherein the candidate answers are generated by a question-answering computer process for answering a question, the candidate answers have associated supporting evidence, and the candidate answers have associated confidence scores, the evidence diffusion module further operable to transfer all or some of the evidence associated with the first candidate answer from the first candidate answer to the second candidate answer based on the identified relationship, the evidence diffusion module further operable to compute a new confidence score for the second candidate answer based on the transferred evidence and an existing evidence associated with the first candidate answer,

wherein the first candidate answer and the second candidate answers have evidence feature attributes of at least passage-text-evidence and transferred-passage-text evidence, and

wherein the evidence associated with the first candidate answer is transferred at least from the passage-text-evidence feature attribute of the first candidate answer to the transferred-passage-text evidence feature attribute of the second candidate answer.

10. The system of claim 9, wherein a direction of transferring between one candidate answer and another candidate answer is controlled based on how the question is posed and types of the candidate answers, wherein the direction of transferring specifies whether to transfer from said one candidate answer to said another candidate answer, or to transfer from said another candidate answer to said one candidate answer.

11. The system of claim 9, wherein the evidence diffusion module transfers evidence by merging the transferred evidence with existing evidence information associated with the second candidate answer.

12. The system of claim 9, wherein the evidence diffusion module transfers evidence by adding a new evidence information denoting direction or strength, or both direction and strength, of the identified one or more relationships.

13. The system of claim 9, wherein the evidence diffusion module transfers evidence by transferring feature scores across candidates.