Patents by Inventor Jacqueline T. Barbetta

Jacqueline T. Barbetta 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).

  • Testing and training a question-answering system
    Patent number: 10936821
    Abstract: An approach is provided for an information handling system that includes a processor and a memory to improve the quality of question-answer sets used as inputs to a question-answering (QA) system. In the approach, a question-answer pair is analyzed using natural language processing (NLP) components. Some of the NLP components may be taken from the QA system whose input is being analyzed The question-answer pair includes a question and an answer to the question. Based on the analysis, one or more shortcomings of the question-answer pair are identified. The shortcomings relate to an ability of the target QA system to analyze the question. A human-readable feedback is provided to a user. The feedback recommends one or more possible actions to address the identified shortcomings.
    Type: Grant
    Filed: July 5, 2016
    Date of Patent: March 2, 2021
    Assignee: International Business Machines Corporation
    Inventors: Jacqueline T. Barbetta, David C. Fallside, Drew A. Logsdon, Peter J. Parente
  • Testing and Training a Question-Answering System
    Publication number: 20160314114
    Abstract: An approach is provided for an information handling system that includes a processor and a memory to improve the quality of question-answer sets used as inputs to a question-answering (QA) system. In the approach, a question-answer pair is analyzed using natural language processing (NLP) components. Some of the NLP components may be taken from the QA system whose input is being analyzed The question-answer pair includes a question and an answer to the question. Based on the analysis, one or more shortcomings of the question-answer pair are identified. The shortcomings relate to an ability of the target QA system to analyze the question. A human-readable feedback is provided to a user. The feedback recommends one or more possible actions to address the identified shortcomings.
    Type: Application
    Filed: July 5, 2016
    Publication date: October 27, 2016
    Inventors: Jacqueline T. Barbetta, David C. Fallside, Drew A. Logsdon, Peter J. Parente
  • Testing and training a question-answering system
    Patent number: 9460085
    Abstract: An approach is provided for an information handling system that includes a processor and a memory to improve the quality of question-answer sets used as inputs to a question-answering (QA) system. In the approach, a question-answer pair is analyzed using natural language processing (NLP) components. Some of the NLP components may be taken from the QA system whose input is being analyzed The question-answer pair includes a question and an answer to the question. Based on the analysis, one or more shortcomings of the question-answer pair are identified. The shortcomings relate to an ability of the target QA system to analyze the question. A human-readable feedback is provided to a user. The feedback recommends one or more possible actions to address the identified shortcomings.
    Type: Grant
    Filed: December 9, 2013
    Date of Patent: October 4, 2016
    Assignee: International Business Machines Corporation
    Inventors: Jacqueline T. Barbetta, David C. Fallside, Drew A. Logsdon, Peter J. Parente
  • Testing and Training a Question-Answering System
    Publication number: 20150161106
    Abstract: An approach is provided for an information handling system that includes a processor and a memory to improve the quality of question-answer sets used as inputs to a question-answering (QA) system. In the approach, a question-answer pair is analyzed using natural language processing (NLP) components. Some of the NLP components may be taken from the QA system whose input is being analyzed The question-answer pair includes a question and an answer to the question. Based on the analysis, one or more shortcomings of the question-answer pair are identified. The shortcomings relate to an ability of the target QA system to analyze the question. A human-readable feedback is provided to a user. The feedback recommends one or more possible actions to address the identified shortcomings.
    Type: Application
    Filed: December 9, 2013
    Publication date: June 11, 2015
    Applicant: International Business Machines Corporation
    Inventors: Jacqueline T. Barbetta, David C. Fallside, Drew A. Logsdon, Peter J. Parente