基於常識知識的移情對話回覆生成

Tzu Hsien Huang, Chia Hui Chang

研究成果: 書貢獻/報告類型會議論文篇章同行評審

1 引文 斯高帕斯(Scopus)

摘要

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 non-pretrained 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.

貢獻的翻譯標題Improving Response Diversity through Commonsense-Aware Empathetic Response Generation
原文繁體中文
主出版物標題ROCLING 2022 - Proceedings of the 34th Conference on Computational Linguistics and Speech Processing
編輯Yung-Chun Chang, Yi-Chin Huang, Jheng-Long Wu, Ming-Hsiang Su, Hen-Hsen Huang, Yi-Fen Liu, Lung-Hao Lee, Chin-Hung Chou, Yuan-Fu Liao
發行者The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)
頁面299-306
頁數8
ISBN(電子)9789869576956
出版狀態已出版 - 2022
事件34th Conference on Computational Linguistics and Speech Processing, ROCLING 2022 - Taipei, Taiwan
持續時間: 21 11月 202222 11月 2022

出版系列

名字ROCLING 2022 - Proceedings of the 34th Conference on Computational Linguistics and Speech Processing

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???34th Conference on Computational Linguistics and Speech Processing, ROCLING 2022
國家/地區Taiwan
城市Taipei
期間21/11/2222/11/22

Keywords

  • Commonsense aware response generation
  • Empathetic response generation
  • response diversity

指紋

深入研究「基於常識知識的移情對話回覆生成」主題。共同形成了獨特的指紋。

引用此