Applying Level of Permanence to Statements to Influence Confidence Ranking

Patent metadata

Field	Value
Publication number	US-2016147757-A1
Application number	US-201414551223-A
Country	US
Kind code	A1
Filing date	Nov 24, 2014
Priority date	Nov 24, 2014
Publication date	May 26, 2016
Grant date	—

Abstract

An approach is provided to identify permanence data corresponding to terms included in a corpus of a question answering (QA) system. Based on the identified permanence, a time-based confidence of each of the terms is established. Terms are identified as a plurality of candidate answers to a question posed to the QA system. Each of the plurality of candidate answers are scored with the scoring being at least partially based on the time-based confidence established for each of the terms.

First claim

1 . (canceled)

2 . (canceled)

3 . (canceled)

4 . (canceled)

5 . (canceled)

6 . (canceled)

7 . (canceled)

8 . 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:
identifying a permanence corresponding to a plurality of terms included in a corpus of a question answering (QA) system;
based on the identified permanence, establishing a time-based confidence of each of the terms;
identifying the terms as a plurality of candidate answers to a question posed to the QA system; and
scoring each of the plurality of candidate answers, wherein the scoring is based on the time-based confidence established for each of the terms.

9 . The information handling system of claim 8 wherein the steps further comprise:
identifying one or more term characteristics pertaining to each of the terms, wherein the term characteristics relate to a rate of change of each of the terms, and wherein the permanence of the terms is identified based on the rate of change of the terms.

10 . The information handling system of claim 9 wherein the steps further comprise:
retrieving a dependency data item corresponding to a selected one of the terms, wherein the dependency data item affects the rate of change of the selected term.

11 . The information handling system of claim 8 wherein the steps further comprise:
identifying a confidence decay type;
selecting a decay algorithm corresponding to the confidence decay type; and
applying the selected decay algorithm to the term, the application of the selected decay algorithm resulting in a prediction of a plurality of term values over a time period for the term.

12 . The information handling system of claim 11 wherein the decay algorithm is a half-life confidence algorithm that predicts a time displacement where a first confidence of a current term value is twice a second confidence of a predicted term value.

13 . The information handling system of claim 8 wherein the steps further comprise:
identifying a plurality of documents as supporting evidence corresponding to the plurality of candidate answers, wherein a score corresponds to each of the plurality of documents;
identifying one or more of the terms with identified permanence that is included in a selected one or the plurality of documents;
applying the identified permanence corresponding to the selected one of the documents, the applying resulting in an adjustment to the score corresponding to the selected one of the documents; and
performing the identifying and the applying for each of the plurality of documents.

14 . The information handling system of claim 8 wherein the steps further comprise:
identifying one or more question characteristics pertaining to the question;
retrieving a permanence metadata corresponding to a selected one of the question characteristics; and
predicting a plurality of values corresponding to the selected question characteristics.

15 . 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:
identifying a permanence corresponding to a plurality of terms included in a corpus of a question answering (QA) system; based on the identified permanence, establishing a time-based confidence of each of the terms; identifying the terms as a plurality of candidate answers to a question posed to the QA system; and scoring each of the plurality of candidate answers, wherein the scoring is based on the time-based confidence established for each of the terms.

16 . The computer program product of claim 15 wherein the steps further comprise:
identifying one or more term characteristics pertaining to each of the terms, wherein the term characteristics relate to a rate of change of each of the terms, and wherein the permanence of the terms is identified based on the rate of change of the terms.

17 . The computer program product of claim 16 wherein the steps further comprise:
retrieving a dependency data item corresponding to a selected one of the terms, wherein the dependency data item affects the rate of change of the selected term.

18 . The computer program product of claim 15 wherein the steps further comprise:
identifying a confidence decay type;
selecting a decay algorithm corresponding to the confidence decay type; and
applying the selected decay algorithm to the term, the application of the selected decay algorithm resulting in a prediction of a plurality of term values over a time period for the term.

19 . The computer program product of claim 18 wherein the decay algorithm is a half-life confidence algorithm that predicts a time displacement where a first confidence of a current term value is twice a second confidence of a predicted term value.

20 . The computer program product of claim 15 wherein the steps further comprise:
identifying a plurality of documents as supporting evidence corresponding to the plurality of candidate answers, wherein a score corresponds to each of the plurality of documents;
identifying one or more of the terms with identified permanence that is included in a selected one or the plurality of documents;
applying the identified permanence corresponding to the selected one of the documents, the applying resulting in an adjustment to the score corresponding to the selected one of the documents; and
performing the identifying and the applying for each of the plurality of documents.

Assignees

• IBM

Inventors

• Adderly Darryl M
• Allen Corville O
• Gerard Scott N
• Tucker Robert K

Classifications

• G06F17/3053 Primary

  Physics · mapped topic

• G06N5/02

  Knowledge representation; Symbolic representation · CPC title

• G06F16/3329

  Natural language query formulation · CPC title

• G06F16/2477 Primary

  Temporal data queries · CPC title

• G06F16/24575

  using context · CPC title