Utilizing Temporal Indicators to Weight Semantic Values

Patent metadata

Field	Value
Publication number	US-2016012335-A1
Application number	US-201514860880-A
Country	US
Kind code	A1
Filing date	Sep 22, 2015
Priority date	Apr 9, 2014
Publication date	Jan 14, 2016
Grant date	—

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 utilizing temporal indicators to weight semantic values. A set of temporal characteristics is identified of a set of initial candidate answers. For each initial candidate answer in the set of initial candidate answers: a distance value is generated for each of the set of temporal characteristics of the set of initial candidate answers, a multiplier value is determined with which to weight an initial confidence score associated with the initial candidate answer using the distance value; a sentiment value is determined of the initial candidate answer, and a final weight value is determined using the multiplier value, the sentiment value, and the initial confidence score associated with the initial candidate answer. A set of temporally refined candidate answers is then provided using the determined final weight values.

First claim

1 . A method, in a data processing system comprising a processor and a memory configured to implement a question and answer system (QA), for utilizing temporal indicators to weight semantic values, the method comprising:
identifying a set of temporal characteristics of a set of initial candidate answers; for each initial candidate answer in the set of initial candidate answers:
generating a distance value for each of the set of temporal characteristics of the set of initial candidate answers;
determining a multiplier value with which to weight an initial confidence score associated with the initial candidate answer using the distance value;
determining a sentiment value of the initial candidate answer; and
determining a final weight value using the multiplier value, the sentiment value, and the initial confidence score associated with the initial candidate answer; and
providing a set of temporally refined candidate answers using the determined final weight values.

2 . The method of claim 1 , wherein the distance value is determined based on a reference time associated with a submitted question.

3 . The method of claim 1 , wherein the multiplier value is determined using a multiplier function:
Multiplier value=1/(2 distance value+0.5)

4 . The method of claim 1 , wherein the final weight value is determined using a distance function:
Final Weight=Initial confidence score*Multiplier Value*Sentiment Value

5 . The method of claim 1 , wherein the sentiment value is +1 if the determined sentiment is positive.

6 . The method of claim I, wherein the sentiment value is −1 if the determined sentiment is negative.

7 . The method of claim 1 , wherein the set of temporally refined candidate answers is ranked according to the determined final weight values.

8 - 20 . (canceled)

Assignees

• IBM

Inventors

• Bufe Iii John P
• Pikovsky Alexander
• Winkler Timothy P

Classifications

• G06F16/3329

  Natural language query formulation · CPC title

• G06F40/30 Primary

  Semantic analysis · CPC title

• G06N5/02 Primary

  Knowledge representation; Symbolic representation · CPC title

• G06F16/90324

  using system suggestions · CPC title

• G06F16/2477

  Temporal data queries · CPC title