Hierarchical graph attention network for relation extraction

doi:10.1088/1742-6596/1780/1/012030

	Hierarchical graph attention network for relation extraction
	Sun,Hongru; Ni,Wancheng; Yang,Yiping
发表期刊	Journal of Physics: Conference Series
ISSN	1742-6588
	2021-02-01
卷号	1780 期号:1
摘要	Abstract Previous research on relation extraction has proved the effectiveness of using dependency trees, which build non-local connections between tokens. However, the existing dependency-based models treat the dependency trees as an inherently flat graph, which causes a loss of dependency information for representing sentences. Besides, they fail to consider the fact that the importance of tokens on the dependency tree varies with different relations to be extracted. In this paper, we propose a novel hierarchical graph attention network HierGAT, which can generate multi-level dependency trees and extract key information from them to improve relation extraction. Specifically, it contains multiple dependency-based graph attention layers, each of which takes a different dependency tree generated by an adaptive subtree pruning strategy as input, and distinguishes the importance of different tokens in a dependency tree. Finally, HierGAT integrates the output token representations of each layer with a multi-head attention mechanism, and learns sentence representation for relation extraction through a pooling layer. The experimental results demonstrate that our method outperforms state-of-the-art baselines on the benchmark datasets.
DOI	10.1088/1742-6596/1780/1/012030
语种	英语
WOS记录号	IOP:1742-6588-1780-1-012030
出版者	IOP Publishing
七大方向——子方向分类	人工智能基础理论
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/43125
专题	综合信息系统研究中心_视知觉融合及其应用复杂系统认知与决策实验室_智能系统与工程
作者单位	Institute of Automation, Chinese Academy of Sciences, Beijing, China
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Sun,Hongru,Ni,Wancheng,Yang,Yiping. Hierarchical graph attention network for relation extraction[J]. Journal of Physics: Conference Series,2021,1780(1).
APA	Sun,Hongru,Ni,Wancheng,&Yang,Yiping.(2021).Hierarchical graph attention network for relation extraction.Journal of Physics: Conference Series,1780(1).
MLA	Sun,Hongru,et al."Hierarchical graph attention network for relation extraction".Journal of Physics: Conference Series 1780.1(2021).