Tzu-Hsien Huang


pdf bib
Improving Response Diversity through Commonsense-Aware Empathetic Response Generation
Tzu-Hsien Huang | Chia-Hui Chang
Proceedings of the 34th Conference on Computational Linguistics and Speech Processing (ROCLING 2022)

Due to the lack of conversation practice, the main challenge for the second-language learners is speaking. Our goal is to develop a chatbot to encourage individuals to reflect, describe, analyse and communicate what they read as well as improve students’ English expression skills. In this paper, we exploit COMMET, an inferential commonsense knowledge generator, as the background knowledge to improve the generation diversity. We consider two approaches to increase the diversity of empathetic response generation. For nonpretrained models, We apply AdaLabel (Wang et al., 2021) to Commonsense-aware Empathetic model (Sabour et al., 2022) and improve Distinct-2 score from 2.99 to 4.08 on EMPATHETIC DIALOGUES (ED). Furthermore, we augment the pretrained BART model with various commonsense knowledge to generate more informative empathetic responses. Not only has the automatic evaluation of distinct-2 scores improved from 9.11 to 11.21, but the manual case study also shows that CE-BART significantly outperform CEM-AdaLabel.