Managing answer feasibility

Patent metadata

Field	Value
Publication number	US-2016180728-A1
Application number	US-201414580376-A
Country	US
Kind code	A1
Filing date	Dec 23, 2014
Priority date	Dec 23, 2014
Publication date	Jun 23, 2016
Grant date	—

Abstract

A system, a method, and a computer program product for managing answer feasibility in a Question and Answering (QA) system. A set of candidate situations is established. The set of candidate situations corresponds to a first set of answers. A QA system establishes the set of candidate situations by analyzing a corpus. The first set of answers will answer a question. The QA system identifies a subset of the set of candidate situations. The subset of candidate situations corresponds to a portion of contextual data. The portion of contextual data is from a set of contextual data. The set of contextual data relates to the question. The question-answering system determines a set of answer feasibility factors. The set of answer feasibility factors is determined using the subset of candidate situations. The set of answer feasibility factors indicates the feasibility of the answers in the first set of answers.

First claim

1 - 16 . (canceled)

17 . A system, 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:
establish, by analyzing a corpus, a set of candidate situations which correspond to a first set of answers for a question;
identify, using natural language processing, a subset of the set of candidate situations which corresponds to a set of contextual data associated with the question; and
determine, using the subset of the set of candidate situations, a set of answer feasibility factors for the first set of answers.

18 . The system of claim 17 , the memory further comprises instructions which, when executed by the processor, cause the processor to:
receive an input including both the question and the set of contextual data; generate, by using a natural language processing technique configured to analyze syntactic and semantic content, the first set of answers, wherein the first set of answers includes:
a first set of media which relates to the input; and
a first set of scores which correspond to the first set of answers;
determine the set of answer feasibility factors by being caused to:
gather, from a subset of the corpus associated with the subset of the set of candidate situations, a set of feasibility evidentiary data; and
determine, using natural language processing on the set of feasibility evidentiary data, a set of score modifiers corresponding with the first set of scores;
map, using a natural language processing technique configured to analyze syntactic and semantic content, the question to a subset of the corpus; compare, using concept-matching, the subset of the corpus to a set of contextually-sensitive categories; classify the subset of the corpus as belonging to a concept of a contextually-sensitive category of the set of contextually-sensitive categories; select, in response to classifying the subset of the corpus as belonging to a concept of a contextually-sensitive category, to use answer feasibility factors; use natural language processing to identify the subset of the set of candidate situations which correspond to the set of contextual data associated with the question by being caused to:
compare, using a concept-matching technique, a first set of terms from a candidate situation of the set of candidate situations to a second set of terms of a corresponding portion of contextual data of the set of contextual data; and
classify the first set of terms as belonging to a linguistic concept of the second set of terms;
detect that the set of contextual data does not contain a portion of contextual data which corresponds to a specific candidate situation of the set of candidate situations; gather the portion of contextual data; add the portion of contextual data to the set of contextual data. generate, using the set of answer feasibility factors and the first set of answers, a second set of answers, wherein the second set of answers is generated by being caused to:
establish, using the first set of media from the first set of candidate answers, a second set of media for the second set of answers;
generate, by applying the set of score modifiers of the set of answer feasibility factors to the first set of scores, a second set of scores; and
map, using a first mapping of the first set of media to the first set of scores, the second set of media to the second set of scores;
identify a score of the second set of scores as meeting an exclusion criterion; and remove, from the second set of answers, an answer which is associated with the score.

19 . 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 first computing device, causes the first computing device to perform a method comprising:
establishing, by analyzing a corpus, a set of candidate situations which correspond to a first set of answers for a question; identifying, using natural language processing, a subset of the set of candidate situations which corresponds to a set of contextual data associated with the question; and determining, using the subset of the set of candidate situations, a set of answer feasibility factors for the first set of answers.

20 . The computer program product of claim 19 , wherein the method further comprises:
receiving an input including both the question and the set of contextual data; generating, by using a natural language processing technique configured to analyze syntactic and semantic content, the first set of answers, wherein the first set of answers includes:
a first set of media which relates to the input; and
a first set of scores which correspond to the first set of answers;
determining the set of answer feasibility factors by:
gathering, from a subset of the corpus associated with the subset of the set of candidate situations, a set of feasibility evidentiary data; and
determining, using natural language processing on the set of feasibility evidentiary data, a set of score modifiers corresponding with the first set of scores;
mapping, using a natural language processing technique configured to analyze syntactic and semantic content, the question to a subset of the corpus; comparing, using concept-matching, the subset of the corpus to a set of contextually-sensitive categories; classifying the subset of the corpus as belonging to a concept of a contextually-sensitive category of the set of contextually-sensitive categories; selecting, in response to classifying the subset of the corpus as belonging to a concept of a contextually-sensitive category, to use answer feasibility factors; using natural language processing to identify the subset of the set of candidate situations which correspond to the set of contextual data associated with the question by:
comparing, using a concept-matching technique, a first set of terms from a candidate situation of the set of candidate situations to a second set of terms of a corresponding portion of contextual data of the set of contextual data; and
classifying the first set of terms as belonging to a linguistic concept of the second set of terms;
detecting that the set of contextual data does not contain a portion of contextual data which corresponds to a specific candidate situation of the set of candidate situations; gathering the portion of contextual data; adding the portion of contextual data to the set of contextual data. generating, using the set of answer feasibility factors and the first set of answers, a second set of answers, wherein the second set of answers is generated by:
establishing, using the first set of media from the first set of candidate answers, a second set of media for the second set of answers;
generating, by applying the set of score modifiers of the set of answer feasibility factors to the first set of scores, a second set of scores; and
mapping, using a first mapping of the first set of media to the first set of scores, the second set of media to the second set of scores;
identifying a score of the second set of scores as meeting an exclusion criterion; and removing, from the second set of answers, an answer which is associated with the score.

Assignees

• IBM

Inventors

• Clark Adam T
• Huebert Jeffrey K
• Payton Aspen L
• Petri John E

Classifications

• G06F40/30 Primary

  Semantic analysis · CPC title

• G09B7/00

  Electrically-operated teaching apparatus or devices working with questions and answers (mechanically operated G09B3/00; computing arrangements G06F) · CPC title

• G06F16/3329

  Natural language query formulation · CPC title

• G09B7/02 Primary

  of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student · CPC title

• G06N5/022

  Knowledge engineering; Knowledge acquisition · CPC title