Graph Based Network with Contextualized Representations of Turns in Dialogue

EMNLP 2021  ·  Bongseok Lee, Yong Suk Choi ·

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

PDF Abstract EMNLP 2021 PDF EMNLP 2021 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Emotion Recognition in Conversation DailyDialog TUCORE-GCN_RoBERTa Micro-F1 61.91 # 3
Emotion Recognition in Conversation DailyDialog TUCORE-GCN_BERT Micro-F1 58.34 # 13
Dialog Relation Extraction DialogRE TUCORE-GCN_RoBERTa F1c (v2) 65.9 # 5
F1 (v2) 73.1 # 4
Dialog Relation Extraction DialogRE TUCORE-GCN_BERT F1c (v2) 60.2 # 9
F1 (v2) 65.5 # 10
Emotion Recognition in Conversation EmoryNLP TUCORE-GCN_BERT Weighted-F1 36.01 # 17
Emotion Recognition in Conversation EmoryNLP TUCORE-GCN_RoBERTa Weighted-F1 39.24 # 6
Emotion Recognition in Conversation MELD TUCORE-GCN_BERT Weighted-F1 62.47 # 30
Emotion Recognition in Conversation MELD TUCORE-GCN_RoBERTa Weighted-F1 65.36 # 19