Full Text:   <420>

CLC number: 

On-line Access: 2022-03-23

Received: 2021-10-18

Revision Accepted: 2022-03-03

Crosschecked: 0000-00-00

Cited: 0

Clicked: 334

Citations:  Bibtex RefMan EndNote GB/T7714

-   Go to

Article info.
Open peer comments

Journal of Zhejiang University SCIENCE C 1998 Vol.-1 No.-1 P.


Improving entity linking with two adaptive features

Author(s):  Hongbin ZHANG, Quan CHEN, Weiwen ZHANG

Affiliation(s):  School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China

Corresponding email(s):   zhangww@gdut.edu.cn

Key Words:  Entity linking, Local model, Global model, Adaptive features, Entity type

Hongbin ZHANG, Quan CHEN, Weiwen ZHANG. Improving entity linking with two adaptive features[J]. Frontiers of Information Technology & Electronic Engineering, 1998, -1(-1): .

@article{title="Improving entity linking with two adaptive features",
author="Hongbin ZHANG, Quan CHEN, Weiwen ZHANG",
journal="Frontiers of Information Technology & Electronic Engineering",
publisher="Zhejiang University Press & Springer",

%0 Journal Article
%T Improving entity linking with two adaptive features
%A Hongbin ZHANG
%A Quan CHEN
%A Weiwen ZHANG
%J Journal of Zhejiang University SCIENCE C
%V -1
%N -1
%@ 2095-9184
%D 1998
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.2100495

T1 - Improving entity linking with two adaptive features
A1 - Hongbin ZHANG
A1 - Quan CHEN
A1 - Weiwen ZHANG
J0 - Journal of Zhejiang University Science C
VL - -1
IS - -1
SP -
EP -
%@ 2095-9184
Y1 - 1998
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.2100495

entity linking (EL) is a fundamental task in natural language processing. Based on neural networks, existing systems pay more attention to construction of the global model, but ignore latent semantic information in the local model and the acquisition of effective entity type information. In this paper, we propose two adaptive features, in which the first adaptive feature enables the local and global models to capture latent information, and the second adaptive feature describes effective information for entity type embeddings. These adaptive features can work together naturally to handle some uncertain entity type information for EL. Experimental results demonstrate that our EL system achieves the best performance on the AIDA-B and MSNBC datasets. It also achieves the highest average performance on out-domain datasets. These results indicate that the proposed adaptive features, which are based on their own diverse contexts, can capture information that is conducive for EL.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Open peer comments: Debate/Discuss/Question/Opinion


Please provide your name, email address and a comment

Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - 2022 Journal of Zhejiang University-SCIENCE