Confidence Ranking of Answers Based on Temporal Semantics

• US 20150293917A1
• Filed: 04/09/2014
• Published: 10/15/2015
• Est. Priority Date: 04/09/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bufe, John P. III, Byron, Donna K., Pikovsky, Alexander, Winkler, Timothy P.
• Granted Patent: US 9,519,686 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/243 Natural language query formulation
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/2477 Temporal data queries
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation

Abstract

A mechanism is provided, in a data processing system comprising a processor and a memory configured to implement a question and answer system (QA), for providing confidence rankings based on temporal semantics. Responsive to receiving an input question, a set of candidate answers is identified from a knowledge domain based on a correlation between an identified one or more predicates and an identified one or more arguments to the knowledge domain. A confidence score is associated with each of the candidate answers and each confidence score associated with each candidate answer is refined based on a set of temporal characteristics identified in the input question. A set of temporally refined candidate answers is then provided to the user.

Claims

1. A method, in a data processing system comprising a processor and a memory configured to implement a question and answer system (QA), for providing confidence rankings based on temporal semantics, the method comprising:

responsive to receiving an input question, identifying a set of candidate answers from a knowledge domain based on a correlation between an identified one or more predicates and an identified one or more arguments to the knowledge domain;

associating a confidence score with each of the candidate answers;

refining each confidence score associated with each candidate answer based on a set of temporal characteristics identified in the input question, wherein each confidence score is refined based on the set of temporal characteristics using a temporal confidence function computed against a temporal interval between a reference time of the question and a respective reference time associated with the set of candidate answers; and

providing a set of temporally refined candidate answers to the user.

2. The method of claim 1, wherein the reference time of the question is identified from the set of temporal characteristics.

3. The method of claim 1, wherein in the reference time is a current time if no temporal characteristics are identifiable in the input question.

4. The method of claim 1, wherein the temporal confidence function is a linear decay function where the confidence of the candidate answer fades smoothly over time.

5. The method of claim 1, wherein the temporal confidence function is a step decay function where the confidence of the candidate answer decays slowly over a predetermined time period.

6. The method of claim 1, wherein the temporal confidence function is a variable decay function based on the knowledge domain.

7. The method of claim 1, wherein the temporal confidence function is populated via at least one of hand-coding or inferred by machine learning techniques.

8. A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a computing device, causes the computing device to:

responsive to receiving an input question, identify a set of candidate answers from a knowledge domain based on a correlation between an identified one or more predicates and an identified one or more arguments to the knowledge domain;

associate a confidence score with each of the candidate answers;

refine each confidence score associated with each candidate answer based on a set of temporal characteristics identified in the input question, wherein each confidence score is refined based on the set of temporal characteristics using a temporal confidence function computed against a temporal interval between a reference time of the question and a respective reference time associated with the set of candidate answers; and

provide a set of temporally refined candidate answers to the user.

9. The computer program product of claim 8, wherein the reference time of the question is identified from the set of temporal characteristics.

10. The computer program product of claim 8, wherein in the reference time is a current time if no temporal characteristics are identifiable in the input question.

11. The computer program product of claim 8, wherein the temporal confidence function is a linear decay function where the confidence of the candidate answer fades smoothly over time.

12. The computer program product of claim 8, wherein the temporal confidence function is a step decay function where the confidence of the candidate answer decays slowly over a predetermined time period.

13. The computer program product of claim 8, wherein the temporal confidence function is a variable decay function based on the knowledge domain.

14. The computer program product of claim 8, wherein the temporal confidence function is populated via at least one of hand-coding or inferred by machine learning techniques.

15. An apparatus comprising:

a processor; and

a memory coupled to the processor, wherein the memory comprises instructions which, when executed by the processor, cause the processor to;

responsive to receiving an input question, identify a set of candidate answers from a knowledge domain based on a correlation between an identified one or more predicates and an identified one or more arguments to the knowledge domain;

associate a confidence score with each of the candidate answers;

refine each confidence score associated with each candidate answer based on a set of temporal characteristics identified in the input question, wherein each confidence score is refined based on the set of temporal characteristics using a temporal confidence function computed against a temporal interval between a reference time of the question and a respective reference time associated with the set of candidate answers; and

provide a set of temporally refined candidate answers to the user.

16. The apparatus of claim 15, wherein the reference time of the question is identified from the set of temporal characteristics.

17. The apparatus of claim 15, wherein in the reference time is a current time if no temporal characteristics are identifiable in the input question.

18. The apparatus of claim 15, wherein the temporal confidence function is a linear decay function where the confidence of the candidate answer fades smoothly over time.

19. The apparatus of claim 15, wherein the temporal confidence function is a step decay function where the confidence of the candidate answer decays slowly over a predetermined time period.

20. The apparatus of claim 15, wherein the temporal confidence function is a variable decay function based on the knowledge domain and wherein the temporal confidence function is populated via at least one of hand-coding or inferred by machine learning techniques.