Graph Based Network with Contextualized Representations of Turns in Dialogue
This addresses the challenge of extracting relations and emotions from dialogues, which have high pronoun usage and low information density, offering a novel approach for natural language understanding tasks.
The paper tackles dialogue-based relation extraction and emotion recognition in conversations by proposing TUCORE-GCN, which uses contextualized turn representations and graph convolutional networks, achieving state-of-the-art performance on multiple benchmark datasets.
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.