公开(公告)号：US20220179858A1

公开(公告)日：2022-06-09

申请号：US17407272

申请日：2021-08-20

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

Inventor： Yan CHEN ,  Kai LIU ,  Jing LIU

IPC: G06F16/2458 ,  G06F16/2453 ,  G06N5/02 ,  G06F40/30

Abstract: The present disclosure provides a generalization processing method, apparatus, device and computer storage medium, and relates to technical field of artificial intelligence and specifically to a deep learning technique. A specific implementation solution is: determining a set of candidate queries in a query library that are similar to a requested query in at least one of a literal matching manner, a semantic matching manner and a query rewriting manner; determining a generalized query corresponding to the requested query from the set of candidate queries by using a pre-trained query matching model; wherein the query matching model is obtained by pre-training based on a cross attention model. The generalization for the requested query can be achieved according to the present disclosure.

公开(公告)号：US20210200956A1

公开(公告)日：2021-07-01

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 ,  G09B7/02 ,  G06F40/258 ,  G06N3/08

Abstract: The present disclosure discloses a method and an apparatus for processing questions and answers, an electronic device and a storage medium. The implementation solution 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, splicing semantic representation vectors obtained through the first semantic representation model of question and the second semantic representation model of question, determining a spliced semantic vector as a semantic representation vector of the question to be answered, acquiring an answer semantic vector matching the semantic representation vector of the question to be answered from a vector index library of answer, and determining an answer corresponding to the answer semantic vector as a target answer to the question to be answered.