arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.05092cs.CL
收藏

基于文档级异构图注意力网络的对话关系抽取

Dialogue Relation Extraction with Document-level Heterogeneous Graph Attention Networks

Singapore University of Technology and Design(新加坡科技设计大学)

Hui Chen, Pengfei Hong, Wei Han, Navonil Majumder, Soujanya Poria

摘要:

对话关系抽取(DRE)的目的是检测在多方对话中提到的两个实体之间的关系。它对于从互联网上日益丰富的会话数据中构建知识图谱,促进智能对话系统的发展具有重要作用。先前的DRE方法并没有有意义地利用说话人信息,它们只是在话语前面加上各自的说话人名字。因此,他们未能模拟关键的说话人之间的关系,可能会通过代词和触发器提供额外的上下文相关的论点实体。然而,我们提出了一个基于图注意力网络的方法DRE的图,其中包含有意义的连接扬声器,实体,实体类型,和话语节点,构建。该图被馈送到图注意力网络,用于在相关节点之间进行上下文传播,从而有效地捕获对话上下文。我们的经验表明,这种基于图的方法非常有效地捕捉了对话中不同实体对之间的关系,因为它在基准数据集DialogRE上的表现明显优于最先进的方法。我们的代码发布于:https://github.com/declare-lab/dialog-HGAT

英文摘要:

Dialogue relation extraction (DRE) aims to detect the relation between two entities mentioned in a multi-party dialogue. It plays an important role in constructing knowledge graphs from conversational data increasingly abundant on the internet and facilitating intelligent dialogue system development. The prior methods of DRE do not meaningfully leverage speaker information-they just prepend the utterances with the respective speaker names. Thus, they fail to model the crucial inter-speaker relations that may give additional context to relevant argument entities through pronouns and triggers. We, however, present a graph attention network-based method for DRE where a graph, that contains meaningfully connected speaker, entity, entity-type, and utterance nodes, is constructed. This graph is fed to a graph attention network for context propagation among relevant nodes, which effectively captures the dialogue context. We empirically show that this graph-based approach quite effectively captures the relations between different entity pairs in a dialogue as it outperforms the state-of-the-art approaches by a significant margin on the benchmark dataset DialogRE. Our code is released at: https://github.com/declare-lab/dialog-HGAT

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。

↑