Patents by Inventor Linlin Chao

Linlin Chao 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).

  • Patent number: 10747959
    Abstract: A dialog generation method includes: training a sequence to sequence (seq2seq)-based dialog model using a loss function including topic range constraint information; and generating a dialog using the trained dialog model. With the dialog generation method, topic range constraint information is introduced in the process of dialog model training using a loss function including the topic range constraint information, thus helping to prevent the trained model from producing low-quality meaningless replies.
    Type: Grant
    Filed: January 31, 2020
    Date of Patent: August 18, 2020
    Assignee: Alibaba Group Holding Limited
    Inventors: Xiaofu Chang, Linlin Chao, Peng Xu, Xiaolong Li
  • Publication number: 20200167528
    Abstract: A dialog generation method includes: training a sequence to sequence (seq2seq)-based dialog model using a loss function including topic range constraint information; and generating a dialog using the trained dialog model. With the dialog generation method, topic range constraint information is introduced in the process of dialog model training using a loss function including the topic range constraint information, thus helping to prevent the trained model from producing low-quality meaningless replies.
    Type: Application
    Filed: January 31, 2020
    Publication date: May 28, 2020
    Inventors: Xiaofu CHANG, Linlin CHAO, Peng XU, Xiaolong LI
  • Publication number: 20200110916
    Abstract: A dialog generation method includes: training a sequence to sequence (seq2seq)-based dialog model using a loss function including topic range constraint information; and generating a dialog using the trained dialog model. With the dialog generation method, topic range constraint information is introduced in the process of dialog model training using a loss function including the topic range constraint information, thus helping to prevent the trained model from producing low-quality meaningless replies.
    Type: Application
    Filed: December 5, 2019
    Publication date: April 9, 2020
    Inventors: Xiaofu CHANG, Linlin Chao, Peng Xu, Xiaolong Li