PLATO-KAG: Unsupervised Knowledge-Grounded Conversation via Joint Modeling
Xinxian Huang, Huang He, Siqi Bao, Fan Wang, Hua Wu, Haifeng Wang
Abstract
Large-scale conversation models are turning to leveraging external knowledge to improve the factual accuracy in response generation. Considering the infeasibility to annotate the external knowledge for large-scale dialogue corpora, it is desirable to learn the knowledge selection and response generation in an unsupervised manner. In this paper, we propose PLATO-KAG (Knowledge-Augmented Generation), an unsupervised learning approach for end-to-end knowledge-grounded conversation modeling. For each dialogue context, the top-k relevant knowledge elements are selected and then employed in knowledge-grounded response generation. The two components of knowledge selection and response generation are optimized jointly and effectively under a balanced objective. Experimental results on two publicly available datasets validate the superiority of PLATO-KAG.- Anthology ID:
- 2021.nlp4convai-1.14
- Volume:
- Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI
- Month:
- November
- Year:
- 2021
- Address:
- Online
- Editors:
- Alexandros Papangelis, Paweł Budzianowski, Bing Liu, Elnaz Nouri, Abhinav Rastogi, Yun-Nung Chen
- Venue:
- NLP4ConvAI
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 143–154
- Language:
- URL:
- https://aclanthology.org/2021.nlp4convai-1.14
- DOI:
- 10.18653/v1/2021.nlp4convai-1.14
- Cite (ACL):
- Xinxian Huang, Huang He, Siqi Bao, Fan Wang, Hua Wu, and Haifeng Wang. 2021. PLATO-KAG: Unsupervised Knowledge-Grounded Conversation via Joint Modeling. In Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI, pages 143–154, Online. Association for Computational Linguistics.
- Cite (Informal):
- PLATO-KAG: Unsupervised Knowledge-Grounded Conversation via Joint Modeling (Huang et al., NLP4ConvAI 2021)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/2021.nlp4convai-1.14.pdf
- Data
- Holl-E, Wizard of Wikipedia