Patents by Inventor Xinpeng CHEN

Xinpeng CHEN 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).

  • Summary generation method, summary generation model training method, and computer device
    Patent number: 11494658
    Abstract: This application relates to an abstract description generating method, an abstract description generation model training method, a computer device, and a storage medium. The abstract description generating method includes: inputting a labeled training sample into an abstract description generation model; performing first-phase training on an encoding network and a decoding network of the abstract description generation model based on supervision of a first loss function; obtaining a backward-derived hidden state of a previous moment through backward derivation according to a hidden state of each moment outputted by the decoding network; obtaining a value of a second loss function according to the backward-derived hidden state of the previous moment and an actual hidden state of the previous moment outputted by the decoding network; and obtaining final model parameters of the abstract description generation model determined based on supervision of the second loss function to reach a preset threshold value.
    Type: Grant
    Filed: November 15, 2019
    Date of Patent: November 8, 2022
    Assignee: Tencent Technology (Shenzhen) Company Limited
    Inventors: Xinpeng Chen, Lin Ma, Wenhao Jiang, Wei Liu
  • SUMMARY GENERATION METHOD, SUMMARY GENERATION MODEL TRAINING METHOD, AND COMPUTER DEVICE
    Publication number: 20200082271
    Abstract: This application relates to an abstract description generating method, an abstract description generation model training method, a computer device, and a storage medium. The abstract description generating method includes: inputting a labeled training sample into an abstract description generation model; performing first-phase training on an encoding network and a decoding network of the abstract description generation model based on supervision of a first loss function; obtaining a backward-derived hidden state of a previous moment through backward derivation according to a hidden state of each moment outputted by the decoding network; obtaining a value of a second loss function according to the backward-derived hidden state of the previous moment and an actual hidden state of the previous moment outputted by the decoding network; and obtaining final model parameters of the abstract description generation model determined based on supervision of the second loss function to reach a preset threshold value.
    Type: Application
    Filed: November 15, 2019
    Publication date: March 12, 2020
    Applicant: Tencent Technology (Shenzhen) Company Limited
    Inventors: Xinpeng CHEN, Lin MA, Wenhao JIANG, Wei LIU