公开(公告)号：US11645316B2

公开(公告)日：2023-05-09

申请号：US17088053

申请日：2020-11-03

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

Inventor： Yingqi Qu ,  Jing Liu

IPC: G06F16/33 ,  G06F16/332 ,  G06F16/338 ,  G06N3/08

CPC classification number: G06F16/3346 ,  G06F16/338 ,  G06F16/3329 ,  G06F16/3344 ,  G06F16/3347 ,  G06N3/08

Abstract: Provided are a question answering method and language model training method, apparatus, device, and storage media, including: acquiring at least one candidate table matching a question to be queried, each candidate table includes a candidate answer corresponding to the question; processing the at least one candidate table to obtain at least one table text, the table text includes textual content of respective fields in the candidate table; inputting the question and each table text into a preset language model respectively to obtain a degree of matching between the question and each candidate table; and outputting a reply table according to the degree of matching of each candidate table, the reply table is a candidate table out of the at least one candidate table whose degree of matching with the question is greater than a preset value or a candidate table that corresponds to a maximum degree of matching.

公开(公告)号：US20230004819A1

公开(公告)日：2023-01-05

申请号：US17930221

申请日：2022-09-07

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

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

IPC: G06N5/00 ,  G06F40/30 ,  G06F16/2457

Abstract: The disclosure provides a method for training a semantic retrieval network, an electronic device and a storage medium. The method includes: obtaining a training sample including a search term and n candidate files corresponding to the search term, where n is an integer greater than 1; inputting the training sample into the ranking model, to obtain n first correlation degrees output by the ranking model, in which each first correlation degree represents a correlation between a candidate document and the search term; inputting the training sample into the semantic retrieval model, to obtain n second correlation degrees output by the semantic retrieval model, wherein each second correlation degree represents a correlation between a candidate document and the search term; and training the semantic retrieval model and the ranking model jointly based on the n first correlation degrees and the n second correlation degrees.