Dialogue Relation Extraction with Document-level Heterogeneous Graph Attention Networks

by   Hui Chen, et al.

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


page 1

page 2

page 3

page 4


DialogRE^C+: An Extension of DialogRE to Investigate How Much Coreference Helps Relation Extraction in Dialogs

Dialogue relation extraction (DRE) that identifies the relations between...

Graph Based Network with Contextualized Representations of Turns in Dialogue

Dialogue-based relation extraction (RE) aims to extract relation(s) betw...

Dialogue-Based Relation Extraction

We present the first human-annotated dialogue-based relation extraction ...

Speaker-Oriented Latent Structures for Dialogue-Based Relation Extraction

Dialogue-based relation extraction (DiaRE) aims to detect the structural...

GraphWOZ: Dialogue Management with Conversational Knowledge Graphs

We present a new approach to dialogue management using conversational kn...

SIRE: Separate Intra- and Inter-sentential Reasoning for Document-level Relation Extraction

Document-level relation extraction has attracted much attention in recen...

Dependency-based Text Graphs for Keyphrase and Summary Extraction with Applications to Interactive Content Retrieval

We build a bridge between neural network-based machine learning and grap...

Code Repositories


Dialogue Relation Extraction with Document-level Heterogeneous Graph Attention Networks

view repo

Please sign up or login with your details

Forgot password? Click here to reset