Abstract
Emotion recognition in conversation (ERC) is an important topic for developing empathetic machines in a variety of areas including social opinion mining, health-care and so on. In this paper, we propose a method to model ERC task as sequence tagging where a Conditional Random Field (CRF) layer is leveraged to learn the emotional consistency in the conversation. We employ LSTM-based encoders that capture self and inter-speaker dependency of interlocutors to generate contextualized utterance representations which are fed into the CRF layer. For capturing long-range global context, we use a multi-layer Transformer encoder to enhance the LSTM-based encoder. Experiments show that our method benefits from modeling the emotional consistency and outperforms the current state-of-the-art methods on multiple emotion classification datasets.- Anthology ID:
- 2020.sigdial-1.23
- Volume:
- Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue
- Month:
- July
- Year:
- 2020
- Address:
- 1st virtual meeting
- Editors:
- Olivier Pietquin, Smaranda Muresan, Vivian Chen, Casey Kennington, David Vandyke, Nina Dethlefs, Koji Inoue, Erik Ekstedt, Stefan Ultes
- Venue:
- SIGDIAL
- SIG:
- SIGDIAL
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 186–195
- Language:
- URL:
- https://aclanthology.org/2020.sigdial-1.23
- DOI:
- 10.18653/v1/2020.sigdial-1.23
- Cite (ACL):
- Yan Wang, Jiayu Zhang, Jun Ma, Shaojun Wang, and Jing Xiao. 2020. Contextualized Emotion Recognition in Conversation as Sequence Tagging. In Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 186–195, 1st virtual meeting. Association for Computational Linguistics.
- Cite (Informal):
- Contextualized Emotion Recognition in Conversation as Sequence Tagging (Wang et al., SIGDIAL 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2020.sigdial-1.23.pdf
- Data
- DailyDialog, IEMOCAP, MELD