公开(公告)号：US20210334659A1

公开(公告)日：2021-10-28

申请号：US17369699

申请日：2021-07-07

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Siyu DING ,  Shuohuan WANG ,  Yu SUN

IPC: G06N3/08 ,  G06N3/04

Abstract: The present application discloses a method and an apparatus for adversarial training of a machine learning (ML) model and a medium. The method includes: obtaining input information in a training sample; extracting features of a plurality of input characters in the input information; inputting the features of the plurality of input characters to the ML model, to capture an attention weight on an input character of the plurality of input characters by an attention layer of the ML model; disturbing the attention weight captured by the attention layer, so that the ML model outputs a predicted character according to the attention weight disturbed; and training the ML model according to a difference between the predicted character and a labeled character in the training sample.

公开(公告)号：US20210248498A1

公开(公告)日：2021-08-12

申请号：US17241999

申请日：2021-04-27

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Chao PANG ,  Shuohuan WANG ,  Yu SUN ,  Zhi LI

IPC: G06N5/04 ,  G06F40/30 ,  G06N20/00

Abstract: A method for training a pre-trained knowledge model includes: obtaining a training text, in which the training text includes a structured knowledge text and an article corresponding to the structured knowledge text, and the structured knowledge text includes a head node, a tail node, and a relationship between the head node and the tail node; and training a pre-trained knowledge model to be trained according to the training text.

公开(公告)号：US20180341698A1

公开(公告)日：2018-11-29

申请号：US15990157

申请日：2018-05-25

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Shuohuan WANG ,  Yu SUN ,  Dianhai YU

IPC: G06F17/30 ,  G06F17/27 ,  G06N5/02 ,  G06N99/00

Abstract: The present disclosure provides a method and apparatus for parsing a query based on artificial intelligence, and a storage medium, wherein the method comprises: regarding any application domain, obtaining a knowledge library corresponding to the application domain; determining a training query serving as a training language material according to the knowledge library; obtaining a deep query parsing model by training according to the training language material; using the deep query parsing model to parse the user's query to obtain a parsing result. The solution of the present disclosure may be applied to improve the accuracy of the parsing result.