Patents by Inventor En Hui ZHUANG

En Hui ZHUANG 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).

  • Machine reading comprehension system for answering queries related to a document
    Patent number: 11899675
    Abstract: A machine reading comprehension system (MRCS) can analyze a larger-sized document that includes multiple pages to predict an answer to a query. For example, the document can have two, five, tens, or hundreds of pages. The MRCS divides the document into multiple sections with each section including a portion of the document. Each section is processed separately by one or more processing circuitries to determine a score for that section. The score indicates how related the section is to the query and/or a probability that the section provides a possible answer to the query. Once all of the sections have been analyzed, the sections are ranked by their scores and a subset of the ranked sections are processed again to determine a predicted answer to the query.
    Type: Grant
    Filed: July 1, 2022
    Date of Patent: February 13, 2024
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Mahmoud Adada, Andrew James McNamara, Kaheer Suleman, Xihui Lin, En Hui Zhuang
  • MACHINE READING COMPREHENSION SYSTEM FOR ANSWERING QUERIES RELATED TO A DOCUMENT
    Publication number: 20220335051
    Abstract: A machine reading comprehension system (MRCS) can analyze a larger-sized document that includes multiple pages to predict an answer to a query. For example, the document can have two, five, tens, or hundreds of pages. The MRCS divides the document into multiple sections with each section including a portion of the document. Each section is processed separately by one or more processing circuitries to determine a score for that section. The score indicates how related the section is to the query and/or a probability that the section provides a possible answer to the query. Once all of the sections have been analyzed, the sections are ranked by their scores and a subset of the ranked sections are processed again to determine a predicted answer to the query.
    Type: Application
    Filed: July 1, 2022
    Publication date: October 20, 2022
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Mahmoud ADADA, Andrew James MCNAMARA, Kaheer SULEMAN, Xihui LIN, En Hui ZHUANG
  • Machine reading comprehension system for answering queries related to a document
    Patent number: 11409749
    Abstract: A machine reading comprehension system (MRCS) can analyze a larger-sized document that includes multiple pages to predict an answer to a query. For example, the document can have two, five, tens, or hundreds of pages. The MRCS divides the document into multiple sections with each section including a portion of the document. Each section is processed separately by one or more processing circuitries to determine a score for that section. The score indicates how related the section is to the query and/or a probability that the section provides a possible answer to the query. Once all of the sections have been analyzed, the sections are ranked by their scores and a subset of the ranked sections are processed again to determine a predicted answer to the query.
    Type: Grant
    Filed: November 9, 2017
    Date of Patent: August 9, 2022
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Mahmoud Adada, Andrew James McNamara, Kaheer Suleman, Xihui Lin, En Hui Zhuang
  • MACHINE READING COMPREHENSION SYSTEM FOR ANSWERING QUERIES RELATED TO A DOCUMENT
    Publication number: 20190138613
    Abstract: A machine reading comprehension system (MRCS) can analyze a larger-sized document that includes multiple pages to predict an answer to a query. For example, the document can have two, five, tens, or hundreds of pages. The MRCS divides the document into multiple sections with each section including a portion of the document. Each section is processed separately by one or more processing circuitries to determine a score for that section. The score indicates how related the section is to the query and/or a probability that the section provides a possible answer to the query. Once all of the sections have been analyzed, the sections are ranked by their scores and a subset of the ranked sections are processed again to determine a predicted answer to the query.
    Type: Application
    Filed: November 9, 2017
    Publication date: May 9, 2019
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Mahmoud ADADA, Andrew James MCNAMARA, Kaheer SULEMAN, Xihui LIN, En Hui ZHUANG