Towards better entity linking  

作　　者：Mingyang LI Yuqing XING Fang KONG Guodong ZHOU 

机构地区：[1]School of Computer Science and Technology,Soochow University,Suzhou 215006,China

出　　处：《Frontiers of Computer Science》2022年第2期55-67,共13页中国计算机科学前沿（英文版）

基　　金：This work was supported by the key project of the National Natural Science Foundation of China(Grant No.61836007);the normal project of the National Natural Science Foundation of China(Grant No.61876118);the project funded by the Priority Academic Program Development of Jiangsu Higher Education Institutions.

摘　　要：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.

关 键 词：entity linking knowledge base extraction selfattention mechanism highway network 

分 类 号：TP311.5[自动化与计算机技术—计算机软件与理论]