Graph Based Network with Contextualized Representations of Turns in Dialogue

TL;DR

This paper introduces TUCORE-GCN, a graph convolutional network that models dialogue context for relation extraction and emotion recognition, outperforming existing models on multiple dialogue understanding benchmarks.

Contribution

The paper presents TUCORE-GCN, a novel graph-based model that effectively captures dialogue context for relation extraction and emotion recognition tasks.

Findings

Outperforms state-of-the-art models on dialogue-based RE datasets

Effective in emotion recognition in conversations

Demonstrates strong generalization across multiple dialogue understanding tasks

Abstract

Dialogue-based relation extraction (RE) aims to extract relation(s) between two arguments that appear in a dialogue. Because dialogues have the characteristics of high personal pronoun occurrences and low information density, and since most relational facts in dialogues are not supported by any single sentence, dialogue-based relation extraction requires a comprehensive understanding of dialogue. In this paper, we propose the TUrn COntext awaRE Graph Convolutional Network (TUCORE-GCN) modeled by paying attention to the way people understand dialogues. In addition, we propose a novel approach which treats the task of emotion recognition in conversations (ERC) as a dialogue-based RE. Experiments on a dialogue-based RE dataset and three ERC datasets demonstrate that our model is very effective in various dialogue-based natural language understanding tasks. In these experiments, TUCORE-GCN outperforms the state-of-the-art models on most of the benchmark datasets. Our code is available at https://github.com/BlackNoodle/TUCORE-GCN.