[go: up one dir, main page]

Relation-aware Graph Attention Networks with Relational Position Encodings for Emotion Recognition in Conversations

Taichi Ishiwatari, Yuki Yasuda, Taro Miyazaki, Jun Goto


Abstract
Interest in emotion recognition in conversations (ERC) has been increasing in various fields, because it can be used to analyze user behaviors and detect fake news. Many recent ERC methods use graph-based neural networks to take the relationships between the utterances of the speakers into account. In particular, the state-of-the-art method considers self- and inter-speaker dependencies in conversations by using relational graph attention networks (RGAT). However, graph-based neural networks do not take sequential information into account. In this paper, we propose relational position encodings that provide RGAT with sequential information reflecting the relational graph structure. Accordingly, our RGAT model can capture both the speaker dependency and the sequential information. Experiments on four ERC datasets show that our model is beneficial to recognizing emotions expressed in conversations. In addition, our approach empirically outperforms the state-of-the-art on all of the benchmark datasets.
Anthology ID:
2020.emnlp-main.597
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7360–7370
Language:
URL:
https://aclanthology.org/2020.emnlp-main.597
DOI:
10.18653/v1/2020.emnlp-main.597
Bibkey:
Cite (ACL):
Taichi Ishiwatari, Yuki Yasuda, Taro Miyazaki, and Jun Goto. 2020. Relation-aware Graph Attention Networks with Relational Position Encodings for Emotion Recognition in Conversations. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7360–7370, Online. Association for Computational Linguistics.
Cite (Informal):
Relation-aware Graph Attention Networks with Relational Position Encodings for Emotion Recognition in Conversations (Ishiwatari et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.597.pdf
Video:
 https://slideslive.com/38938698
Data
DailyDialogEmoryNLPIEMOCAPMELD