Multi-Task Learning of Generation and Classification for Emotion-Aware Dialogue Response Generation

Tatsuya Ide, Daisuke Kawahara


Abstract
For a computer to naturally interact with a human, it needs to be human-like. In this paper, we propose a neural response generation model with multi-task learning of generation and classification, focusing on emotion. Our model based on BART (Lewis et al., 2020), a pre-trained transformer encoder-decoder model, is trained to generate responses and recognize emotions simultaneously. Furthermore, we weight the losses for the tasks to control the update of parameters. Automatic evaluations and crowdsourced manual evaluations show that the proposed model makes generated responses more emotionally aware.
Anthology ID:
2021.naacl-srw.15
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop
Month:
June
Year:
2021
Address:
Online
Editors:
Esin Durmus, Vivek Gupta, Nelson Liu, Nanyun Peng, Yu Su
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
119–125
Language:
URL:
https://aclanthology.org/2021.naacl-srw.15
DOI:
10.18653/v1/2021.naacl-srw.15
Bibkey:
Cite (ACL):
Tatsuya Ide and Daisuke Kawahara. 2021. Multi-Task Learning of Generation and Classification for Emotion-Aware Dialogue Response Generation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop, pages 119–125, Online. Association for Computational Linguistics.
Cite (Informal):
Multi-Task Learning of Generation and Classification for Emotion-Aware Dialogue Response Generation (Ide & Kawahara, NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-srw.15.pdf
Video:
 https://aclanthology.org/2021.naacl-srw.15.mp4
Data
DailyDialogSSTSST-2