公开(公告)号：US10929452B2

公开(公告)日：2021-02-23

申请号：US16688090

申请日：2019-11-19

Applicant: Huawei Technologies Co., Ltd.

Inventor： Piji Li ,  Zhengdong Lu ,  Hang Li

IPC: G06F3/048 ,  G06F16/34 ,  G06N20/00 ,  G06F40/211 ,  G06F40/289 ,  G06F17/16

Abstract: A multi-document summary generation method includes obtaining a candidate sentence set, training each candidate sentence in the candidate sentence set using a cascaded attention mechanism and an unsupervised learning model in a preset network model, to obtain importance of each candidate sentence, selecting, based on the importance of each candidate sentence, a phrase that meets a preset condition from the candidate sentence set as a summary phrase set, and obtaining a summary of a plurality of candidate documents based on the summary phrase set.

公开(公告)号：US20200081909A1

公开(公告)日：2020-03-12

申请号：US16688090

申请日：2019-11-19

Applicant: Huawei Technologies Co., Ltd.

Inventor： Piji Li ,  Zhengdong Lu ,  Hang Li

IPC: G06F16/34 ,  G06N20/00 ,  G06F17/16 ,  G06F17/27

Abstract: A multi-document summary generation method includes obtaining a candidate sentence set, training each candidate sentence in the candidate sentence set using a cascaded attention mechanism and an unsupervised learning model in a preset network model, to obtain importance of each candidate sentence, selecting, based on the importance of each candidate sentence, a phrase that meets a preset condition from the candidate sentence set as a summary phrase set, and obtaining a summary of a plurality of candidate documents based on the summary phrase set.