Categorizing users based on similarity of posed questions, answers and supporting evidence

摘要

Mechanisms are provided for performing an operation based on an identification of similar lines of questioning by input question sources. Question information identifying extracted features of an input question and a first source of the input question is obtained. A clustering operation is performed to cluster the input question with one or more other questions of a cluster based on a similarity of the extracted features of the input question to features of the one or more other questions. An operation is performed based on results of the clustering of the input question with the one or more other questions.

主权项

1. A computer program product comprising a non-transitory computer readable medium having a computer readable program stored therein, wherein the computer readable program, when executed on a computing device, causes the computing device to:
obtain question information identifying extracted features of an input question and a first source of the input question; perform a clustering operation to cluster the input question with one or more other questions of a cluster based on a similarity of the extracted features of the input question to features of the one or more other questions; and perform an operation based on results of the clustering of the input question with the one or more other questions, wherein the operation comprises at least one of initiating a collaboration between the first source of the input question and a second source of another question in the cluster, initiating a communication between the first source and the second source, or a reporting of the results of the clustering operation to either the first source, the second source, or a third party, wherein:
the input question is a question input to a Question and Answer (QA) system which processes the input question to generate an answer to the input question based on a corpus of information, and further generates one or more supporting evidence passages supporting the answer as being a correct answer for the input question, andthe computer readable program further causes the computing device to perform the clustering operation to cluster the input question with the one or more other questions of a cluster at least by performing the clustering based on features of the input question, features of an answer, and features of the one or more supporting evidence passages,wherein the computer readable program further causes the computing device to, for the input question, generate one or more question (Q)-Answer (A)-evidence Passage (P) triplets, and wherein performing the clustering operation comprises performing clustering on features of each of the Question (Q), Answer (A), and evidence Passage (P) of the one or more QAP triplets with features of QAP triplets associated with questions in a plurality of previously processed questions to thereby identify the one or more other questions of the cluster with which the input question is clustered.