Title:
エンティティ・リンキング方法、装置、機器、及び記憶媒体
Document Type and Number:
Japanese Patent JP7317791
Kind Code:
B2
Abstract:
The present disclosure discloses a method, apparatus, device, and storage medium for linking an entity, relates to the technical fields of knowledge graph and deep learning. A specific implementation is: acquiring a target text; determining at least one entity mention included in the target text and a candidate entity corresponding to each entity mention; determining an embedding vector of each candidate entity based on the each candidate entity and a preset entity embedding vector determination model; determining context semantic information of the target text based on the target text and each embedding vector; determining type information of the at least one entity mention; and determining an entity linking result of the at least one entity mention, based on the each embedding vector, the context semantic information, and each type information. This implementation can make full use of external knowledge, thereby improving the accuracy of the entity linking.
Inventors:
Liu Jie
Wan Chi
Huong Jiefang
Chai Chunguan
Ju Young
Wan Chi
Huong Jiefang
Chai Chunguan
Ju Young
Application Number:
JP2020206160A
Publication Date:
July 31, 2023
Filing Date:
December 11, 2020
Export Citation:
Assignee:
Beijing Baidu Netcom Science Technology Co., Ltd.
International Classes:
G06F16/383; G06F16/90
Domestic Patent References:
JP2019049964A |
Foreign References:
WO2020003928A1 | ||||
WO2015125209A1 | ||||
WO2019224891A1 |
Attorney, Agent or Firm:
Nagoya International Patent Attorney Corporation