公开(公告)号：US11461556B2

公开(公告)日：2022-10-04

申请号：US16886244

申请日：2020-05-28

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

Inventor： Yuchen Ding ,  Kai Liu ,  Jing Liu ,  Yan Chen

IPC: G06F40/30 ,  G06F40/258 ,  G06N3/08 ,  G09B7/02

Abstract: A method for processing questions and answers includes: in a process of determining an answer to a question to be answered, determining the semantic representation on the question to be answered respectively with a first semantic representation model of question and a second semantic representation model of question. Semantic representation vectors obtained through the first semantic representation model of question and the second semantic representation model of question are spliced. A spliced semantic vector is determined as a semantic representation vector of the question to be answered. An answer semantic vector matching the semantic representation vector of the question to be answered is acquired from a vector index library of answer, and an answer corresponding to the answer semantic vector is determined as a target answer to the question to be answered.

公开(公告)号：US11847150B2

公开(公告)日：2023-12-19

申请号：US17407320

申请日：2021-08-20

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

Inventor： Yuchen Ding ,  Yingqi Qu ,  Jing Liu ,  Kai Liu ,  Dou Hong ,  Hua Wu ,  Haifeng Wang

IPC: G06F16/33 ,  G06N20/20

CPC classification number: G06F16/3347 ,  G06F16/3344 ,  G06N20/20

Abstract: The present application discloses a method and apparatus for training a retrieval model, device and computer storage medium that relate to intelligent search and natural language processing technologies. An implementation includes: acquiring initial training data; performing a training operation using the initial training data to obtain an initial retrieval model; selecting texts with the correlation degrees with a query in the training data meeting a preset first requirement from candidate texts using the initial retrieval model; performing a training operation using the updated training data to obtain a first retrieval model; and selecting texts with the correlation degrees with the query in the training data meeting a preset second requirement from the candidate texts using the first retrieval model; and/or selecting texts with the correlation degrees with the query meeting a preset third requirement; and performing a training operation using the expanded training data to obtain a second retrieval model.