English

Commonsense-Aware Prompting for Controllable Empathetic Dialogue Generation

Computation and Language 2023-02-06 v1 Machine Learning

Abstract

Improving the emotional awareness of pre-trained language models is an emerging important problem for dialogue generation tasks. Although prior studies have introduced methods to improve empathetic dialogue generation, few have discussed how to incorporate commonsense knowledge into pre-trained language models for controllable dialogue generation. In this study, we propose a novel framework that improves empathetic dialogue generation using pre-trained language models by 1) incorporating commonsense knowledge through prompt verbalization, and 2) controlling dialogue generation using a strategy-driven future discriminator. We conducted experiments to reveal that both the incorporation of social commonsense knowledge and enforcement of control over generation help to improve generation performance. Finally, we discuss the implications of our study for future research.

Keywords

Cite

@article{arxiv.2302.01441,
  title  = {Commonsense-Aware Prompting for Controllable Empathetic Dialogue Generation},
  author = {Yiren Liu and Halil Kilicoglu},
  journal= {arXiv preprint arXiv:2302.01441},
  year   = {2023}
}

Comments

Accepted to Workshop on Knowledge Augmented Methods for Natural Language Processing, in conjunction with AAAI 2023

R2 v1 2026-06-28T08:30:52.325Z