Patents by Inventor Wutao LIN

Wutao LIN 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).

  • Method and apparatus for building synonymy discriminating model and method and apparatus for discriminating synonymous text
    Patent number: 10776578
    Abstract: A method for building the synonymy discriminating model comprises: obtaining a text pair in training samples; using a word vector dictionary to obtain a quantization matrix of texts in the text pair; regarding the quantization matrix of respective texts as input of a convolutional neural network, regarding a synonymy annotation result corresponding to the text pair as output of the convolutional neural network, and training the convolutional neural network to obtain a synonymy discriminating model. The method for discriminating the synonymous text comprises: obtaining a text pair to be discriminated; using a word vector dictionary to obtain a quantization matrix corresponding to texts in the text pair; regarding the quantization matrix of the texts as input of a synonymy discriminating model, and determining a synonymy discrimination result of the text pair according to output of the synonymy discriminating model.
    Type: Grant
    Filed: August 30, 2018
    Date of Patent: September 15, 2020
    Assignee: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.
    Inventors: Miao Fan, Mingming Sun, Wutao Lin, Ping Li
  • METHOD AND APPARATUS FOR BUILDING SYNONYMY DISCRIMINATING MODEL AND METHOD AND APPARATUS FOR DISCRIMINATING SYNONYMOUS TEXT
    Publication number: 20190095429
    Abstract: A method for building the synonymy discriminating model comprises: obtaining a text pair in training samples; using a word vector dictionary to obtain a quantization matrix of texts in the text pair; regarding the quantization matrix of respective texts as input of a convolutional neural network, regarding a synonymy annotation result corresponding to the text pair as output of the convolutional neural network, and training the convolutional neural network to obtain a synonymy discriminating model. The method for discriminating the synonymous text comprises: obtaining a text pair to be discriminated; using a word vector dictionary to obtain a quantization matrix corresponding to texts in the text pair; regarding the quantization matrix of the texts as input of a synonymy discriminating model, and determining a synonymy discrimination result of the text pair according to output of the synonymy discriminating model.
    Type: Application
    Filed: August 30, 2018
    Publication date: March 28, 2019
    Applicant: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.
    Inventors: Miao FAN, Mingming SUN, Wutao LIN, Ping LI