Patents by Inventor Srinivasa Phani K. Gadde

Srinivasa Phani K. Gadde 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).

  • Determining off-topic questions in a question answering system using probabilistic language models
    Patent number: 10713438
    Abstract: A question answering system that determines whether a question is off-topic by performing the following steps: (i) receiving, by a question answering system, a set of documents; (ii) identifying topical subset(s) for each document of the set of documents using named entity recognition, where each topical subset relates to a corresponding topic; (iii) assigning a set of topic score(s) for each topical subset using natural language processing, where each topic score relates to a corresponding probability associated with the respective topical subset under a probabilistic language model; and (iv) determining, based, at least in part, on the topic score(s) corresponding to the topical subset(s), whether a question input into the question answering system is off-topic.
    Type: Grant
    Filed: June 15, 2016
    Date of Patent: July 14, 2020
    Assignee: International Business Machines Corporation
    Inventors: John P. Bufe, Srinivasa Phani K. Gadde, Julius Goth, III
  • Determining off-topic questions in a question answering system using probabilistic language models
    Patent number: 10372819
    Abstract: A question answering system that determines whether a question is off-topic by performing the following steps: (i) receiving, by a question answering system, a set of documents; (ii) identifying topical subset(s) for each document of the set of documents using named entity recognition, where each topical subset relates to a corresponding topic; (iii) assigning a set of topic score(s) for each topical subset using natural language processing, where each topic score relates to a corresponding probability associated with the respective topical subset under a probabilistic language model; and (iv) determining, based, at least in part, on the topic score(s) corresponding to the topical subset(s), whether a question input into the question answering system is off-topic.
    Type: Grant
    Filed: March 23, 2015
    Date of Patent: August 6, 2019
    Assignee: International Business Machines Corporation
    Inventors: John P. Bufe, Srinivasa Phani K. Gadde, Julius Goth, III
  • DETERMINING OFF-TOPIC QUESTIONS IN A QUESTION ANSWERING SYSTEM USING PROBABILISTIC LANGUAGE MODELS
    Publication number: 20160300154
    Abstract: A question answering system that determines whether a question is off-topic by performing the following steps: (i) receiving, by a question answering system, a set of documents; (ii) identifying topical subset(s) for each document of the set of documents using named entity recognition, where each topical subset relates to a corresponding topic; (iii) assigning a set of topic score(s) for each topical subset using natural language processing, where each topic score relates to a corresponding probability associated with the respective topical subset under a probabilistic language model; and (iv) determining, based, at least in part, on the topic score(s) corresponding to the topical subset(s), whether a question input into the question answering system is off-topic.
    Type: Application
    Filed: June 15, 2016
    Publication date: October 13, 2016
    Inventors: John P. Bufe, Srinivasa Phani K. Gadde, Julius Goth, III
  • DETERMINING OFF-TOPIC QUESTIONS IN A QUESTION ANSWERING SYSTEM USING PROBABILISTIC LANGUAGE MODELS
    Publication number: 20160283851
    Abstract: A question answering system that determines whether a question is off-topic by performing the following steps: (i) receiving, by a question answering system, a set of documents; (ii) identifying topical subset(s) for each document of the set of documents using named entity recognition, where each topical subset relates to a corresponding topic; (iii) assigning a set of topic score(s) for each topical subset using natural language processing, where each topic score relates to a corresponding probability associated with the respective topical subset under a probabilistic language model; and (iv) determining, based, at least in part, on the topic score(s) corresponding to the topical subset(s), whether a question input into the question answering system is off-topic.
    Type: Application
    Filed: March 23, 2015
    Publication date: September 29, 2016
    Inventors: John P. Bufe, Srinivasa Phani K. Gadde, Julius Goth, III