Emp-RFT: Empathetic Response Generation via Recognizing Feature Transitions between Utterances
Wongyu Kim, Youbin Ahn, Donghyun Kim, Kyong-Ho Lee
Abstract
Each utterance in multi-turn empathetic dialogues has features such as emotion, keywords, and utterance-level meaning. Feature transitions between utterances occur naturally. However, existing approaches fail to perceive the transitions because they extract features for the context at the coarse-grained level. To solve the above issue, we propose a novel approach of recognizing feature transitions between utterances, which helps understand the dialogue flow and better grasp the features of utterance that needs attention. Also, we introduce a response generation strategy to help focus on emotion and keywords related to appropriate features when generating responses. Experimental results show that our approach outperforms baselines and especially, achieves significant improvements on multi-turn dialogues.
BibTeX
@inproceedings{kim-etal-2022-emp,
title = "Emp-{RFT}: Empathetic Response Generation via Recognizing Feature Transitions between Utterances",
author = "Kim, Wongyu and
Ahn, Youbin and
Kim, Donghyun and
Lee, Kyong-Ho",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.303/",
doi = "10.18653/v1/2022.naacl-main.303",
pages = "4118--4128"
}