arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.10624cs.CLcs.IR
收藏

用于改进关系抽取的上下文图注意力

Contextualised Graph Attention for Improved Relation Extraction

University of Liverpool(利物浦大学)

Angrosh Mandya, Danushka Bollegala, Frans Coenen

摘要:

本文提出了一种结合边缘特征和多子图的上下文化图注意力网络,用于改进关系抽取。提出了一种利用多子图学习图网络中富节点表示的新方法。为此,从单个依赖关系树获得多个子图。提出了两类边缘特征,并将其与GAT和GCN模型有效结合,应用于关系抽取。该模型在Semeval 2010 Task 8数据集上实现了最先进的性能,F1得分为86.3。

英文摘要:

This paper presents a contextualized graph attention network that combines edge features and multiple sub-graphs for improving relation extraction. A novel method is proposed to use multiple sub-graphs to learn rich node representations in graph-based networks. To this end multiple sub-graphs are obtained from a single dependency tree. Two types of edge features are proposed, which are effectively combined with GAT and GCN models to apply for relation extraction. The proposed model achieves state-of-the-art performance on Semeval 2010 Task 8 dataset, achieving an F1-score of 86.3.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑