HyperED: A hierarchy-aware network based on hyperbolic geometry for event detection

首页 > 成果 > 详情

认领

导出

Link by DOI

反馈

作者信息关键词期刊信息基础信息归属信息摘要

成果类型：

期刊论文

作者：

Zhang, Meng;Xie, Zhiwen;Liu, Jin;Liu, Xiao;Yu, Xiao;...

通讯作者：

Liu, J

作者机构：

[Liu, Jin; Zhang, Meng] Wuhan Univ, Sch Comp Sci, Wuhan, Peoples R China.

[Xie, Zhiwen] Cent China Normal Univ, Sch Comp Sci, Wuhan, Peoples R China.

[Liu, Xiao] Deakin Univ, Sch Informat Technol, Geelong, Australia.

[Yu, Xiao] Wuhan Univ Technol, Sch Comp Sci & Artificial Intelligence, Wuhan, Peoples R China.

[Huang, Bo] Shanghai Univ Engn Sci, Sch Elect & Elect Engn, Shanghai, Peoples R China.

通讯机构：

[Liu, J ] W

Wuhan Univ, Sch Comp Sci, Wuhan 430072, Peoples R China.

语种：

英文

关键词：

event detection;hierarchical information;graph neural networks;hyperbolic geometry;Poincare ball

期刊：

Computational Intelligence

ISSN：

0824-7935

年：

2024

卷：

期：

页码：

DOI：

10.1111/coin.12627

基金类别：

National Natural Science Foundation of China

机构署名：

本校为其他机构

院系归属：

计算机学院

摘要：

Abstract Event detection plays an essential role in the task of event extraction. It aims at identifying event trigger words in a sentence and classifying event types. Generally, multiple event types are usually well‐organized with a hierarchical structure in real‐world scenarios, and hierarchical correlations between event types can be used to enhance event detection performance. However, such kind of hierarchical information has received insufficient attention which can lead to misclassification between multiple event types. In addition, th...

反馈

产权有误：本人成果被他人认领

数据有误：数据基本信息有误

归属有误：成果的院系归属、机构署名归属有误

其他原因：

验证码：

看不清楚，换一个

确定

取消

成果认领

标题：

用户	作者	通讯作者	--
	请选择	请选择	--

确定

取消

HyperED: A hierarchy-aware network based on hyperbolic geometry for event detection

反馈

成果认领

提示

该栏目需要登录且有访问权限才可以访问