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...
Saved in:
Published in | Frontiers of Computer Science Vol. 16; no. 2; p. 162308 |
---|---|
Main Authors | , , , |
Format | Journal Article |
Language | English |
Published |
Beijing
Higher Education Press
01.04.2022
Springer Nature B.V |
Subjects | |
Online Access | Get full text |
Cover
Loading…
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 |