Patents by Inventor Akari ASAI

Akari ASAI 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).

  • Systems and Methods for Reading Comprehension for a Question Answering Task
    Publication number: 20230419050
    Abstract: Embodiments described herein provide a pipelined natural language question answering system that improves a BERT-based system. Specifically, the natural language question answering system uses a pipeline of neural networks each trained to perform a particular task. The context selection network identifies premium context from context for the question. The question type network identifies the natural language question as a yes, no, or span question and a yes or no answer to the natural language question when the question is a yes or no question. The span extraction model determines an answer span to the natural language question when the question is a span question.
    Type: Application
    Filed: September 7, 2023
    Publication date: December 28, 2023
    Inventors: Akari ASAI, Kazuma HASHIMOTO, Richard SOCHER, Caiming XIONG
  • Systems and methods for reading comprehension for a question answering task
    Patent number: 11775775
    Abstract: Embodiments described herein provide a pipelined natural language question answering system that improves a BERT-based system. Specifically, the natural language question answering system uses a pipeline of neural networks each trained to perform a particular task. The context selection network identifies premium context from context for the question. The question type network identifies the natural language question as a yes, no, or span question and a yes or no answer to the natural language question when the question is a yes or no question. The span extraction model determines an answer span to the natural language question when the question is a span question.
    Type: Grant
    Filed: November 26, 2019
    Date of Patent: October 3, 2023
    Assignee: Salesforce.com, Inc.
    Inventors: Akari Asai, Kazuma Hashimoto, Richard Socher, Caiming Xiong
  • Systems and Methods for Reading Comprehension for a Question Answering Task
    Publication number: 20200372341
    Abstract: Embodiments described herein provide a pipelined natural language question answering system that improves a BERT-based system. Specifically, the natural language question answering system uses a pipeline of neural networks each trained to perform a particular task. The context selection network identifies premium context from context for the question. The question type network identifies the natural language question as a yes, no, or span question and a yes or no answer to the natural language question when the question is a yes or no question. The span extraction model determines an answer span to the natural language question when the question is a span question.
    Type: Application
    Filed: November 26, 2019
    Publication date: November 26, 2020
    Inventors: Akari ASAI, Kazuma HASHIMOTO, Richard SOCHER, Caiming XIONG