Towards better entity linking

As one of the most important components in knowledge graph construction, entity linking has been drawing more and more attention in the last decade. In this paper, we propose two improvements towards better entity linking. On one hand, we propose a simple but effective coarse-to-fine unsupervised kn...

Full description

Saved in:
Bibliographic Details
Published inFrontiers of Computer Science Vol. 16; no. 2; p. 162308
Main Authors LI, Mingyang, XING, Yuqing, KONG, Fang, ZHOU, Guodong
Format Journal Article
LanguageEnglish
Published Beijing Higher Education Press 01.04.2022
Springer Nature B.V
Subjects
Candidates
Computer Science
entity linking
highway network
Knowledge
knowledge base extraction
Knowledge bases (artificial intelligence)
Knowledge representation
Research Article
Search engines
selfattention mechanism
Semantics
Soccer
Tournaments & championships
knowledge base extraction
selfatention mechanism
highway network
entity linking
Online AccessGet full text

Cover

More Information
Summary:As one of the most important components in knowledge graph construction, entity linking has been drawing more and more attention in the last decade. In this paper, we propose two improvements towards better entity linking. On one hand, we propose a simple but effective coarse-to-fine unsupervised knowledge base(KB) extraction approach to improve the quality of KB, through which we can conduct entity linking more efficiently. On the other hand, we propose a highway network framework to bridge key words and sequential information captured with a self-attention mechanism to better represent both local and global information. Detailed experimentation on six public entity linking datasets verifies the great effectiveness of both our approaches.
Bibliography:knowledge base extraction
Document received on :2020-05-11
highway network
selfattention mechanism
entity linking
Document accepted on :2020-08-20
ISSN:2095-2228
2095-2236
DOI:10.1007/S11704-020-0192-9