A Discourse-Aware Graph Neural Network for Emotion Recognition in Multi-Party Conversation

Yang Sun, Nan Yu, Guohong Fu


Abstract
Emotion recognition in multi-party conversation (ERMC) is becoming increasingly popular as an emerging research topic in natural language processing. Prior research focuses on exploring sequential information but ignores the discourse structures of conversations. In this paper, we investigate the importance of discourse structures in handling informative contextual cues and speaker-specific features for ERMC. To this end, we propose a discourse-aware graph neural network (ERMC-DisGCN) for ERMC. In particular, we design a relational convolution to lever the self-speaker dependency of interlocutors to propagate contextual information. Furthermore, we exploit a gated convolution to select more informative cues for ERMC from dependent utterances. The experimental results show our method outperforms multiple baselines, illustrating that discourse structures are of great value to ERMC.
Anthology ID:
2021.findings-emnlp.252
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2949–2958
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.252
DOI:
10.18653/v1/2021.findings-emnlp.252
Bibkey:
Cite (ACL):
Yang Sun, Nan Yu, and Guohong Fu. 2021. A Discourse-Aware Graph Neural Network for Emotion Recognition in Multi-Party Conversation. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2949–2958, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
A Discourse-Aware Graph Neural Network for Emotion Recognition in Multi-Party Conversation (Sun et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.252.pdf
Video:
 https://aclanthology.org/2021.findings-emnlp.252.mp4
Data
EmoryNLPIEMOCAPMELD