Patents by Inventor William A. Beason

William A. Beason has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Domain-specific question-answer pair generation
    Patent number: 10170014
    Abstract: A computer-implemented method for creating question-answer pairs is provided. The computer-implemented method includes leveraging domain specific resources including, at least one or more of lexicons, glossaries, or knowledge bases for constructing templates for creating the question-answer pairs. The computer implemented method further includes leveraging user experiences of a plurality of users for constructing templates. The computer implemented method further includes eliminating erroneous question-answer pairs based on templates specifications of a heuristic process of the constructed templates.
    Type: Grant
    Filed: July 28, 2015
    Date of Patent: January 1, 2019
    Assignee: International Business Machines Corporation
    Inventors: William A. Beason, Swaminathan Chandrasekaran, Anne E. Gattiker, Lakshminarayanan Krishnamurthy, Sridhar Sudarsan
  • Identifying vague questions in a question-answer system
    Patent number: 9690774
    Abstract: An approach is provided that improves a question answering (QA) computer system by reducing a number of vague questions submitted to the QA system. When a question is submitted to the QA system, the approach performs a vagueness question analysis on the question. The vagueness question analysis results in a vagueness score. The question is submitted to the QA system in response to the vagueness score reaching a threshold value that indicates a lack of vagueness in the question. The approach inhibits submission of the question to the QA system in response to the vagueness score failing to reach the threshold value.
    Type: Grant
    Filed: December 16, 2015
    Date of Patent: June 27, 2017
    Assignee: International Business Machines Corporation
    Inventors: William A. Beason, Vincent J. Dowling, Anne E. Gattiker, Lakshminarayanan Krishnamurthy, Joseph N. Kozhaya
  • Identifying Vague Questions in a Question-Answer System
    Publication number: 20170177565
    Abstract: An approach is provided that improves a question answering (QA) computer system by reducing a number of vague questions submitted to the QA system. When a question is submitted to the QA system, the approach performs a vagueness question analysis on the question. The vagueness question analysis results in a vagueness score. The question is submitted to the QA system in response to the vagueness score reaching a threshold value that indicates a lack of vagueness in the question. The approach inhibits submission of the question to the QA system in response to the vagueness score failing to reach the threshold value.
    Type: Application
    Filed: December 16, 2015
    Publication date: June 22, 2017
    Inventors: William A. Beason, Vincent J. Dowling, Anne E. Gattiker, Lakshminarayanan Krishnamurthy, Joseph N. Kozhaya
  • DOMAIN-SPECIFIC QUESTION-ANSWER PAIR GENERATION
    Publication number: 20170032689
    Abstract: A computer-implemented method for creating question-answer pairs is provided. The computer-implemented method includes leveraging domain specific resources including, at least one or more of lexicons, glossaries, or knowledge bases for constructing templates for creating the question-answer pairs. The computer implemented method further includes leveraging user experiences of a plurality of users for constructing templates. The computer implemented method further includes eliminating erroneous question-answer pairs based on templates specifications of a heuristic process of the constructed templates.
    Type: Application
    Filed: July 28, 2015
    Publication date: February 2, 2017
    Inventors: William A. Beason, Swaminathan Chandrasekaran, Anne E. Gattiker, Lakshminarayanan Krishnamurthy, Sridhar Sudarsan