论文标题
与文档级异质图注意网络的对话关系提取
Dialogue Relation Extraction with Document-level Heterogeneous Graph Attention Networks
论文作者
论文摘要
对话关系提取（DRE）旨在检测多方对话中提到的两个实体之间的关系。它在从互联网上越来越丰富的对话数据中构建知识图并促进智能对话系统开发中起着重要作用。 DRE的先前方法没有有意义地利用说话者信息 - 他们只是用各自的演讲者名称来预言话语。因此，他们无法建模至关重要的言论扬声器关系，该关系可能会通过代词和触发器为相关参数实体提供其他上下文。但是，我们提出了一种基于图形的DRE的基于图形的方法，其中包含有意义连接的说话者，实体，实体类型和话语节点的图形。该图被馈送到图表网络中，以在相关节点之间进行上下文传播，从而有效地捕获了对话上下文。我们从经验上表明，这种基于图的方法非常有效地捕获了对话中不同实体对之间的关系，因为它在基准数据集对话框上的大幅度优于最先进的方法。我们的代码在以下网址发布：https：//github.com/declare-lab/dialog-hgat
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
