Dialogue Relation Extraction with Document-level Heterogeneous Graph Attention Networks

10 Sep 2020  ·  Hui Chen, Pengfei Hong, Wei Han, Navonil Majumder, Soujanya Poria ·

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

PDF Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Dialog Relation Extraction DialogRE DHGAT F1 (v1) 56.1 # 9
F1c (v1) 50.7 # 7


No methods listed for this paper. Add relevant methods here