Retrieval-free Knowledge Injection through Multi-Document Traversal for Dialogue Models
Rui Wang, Jianzhu Bao, Fei Mi, Yi Chen, Hongru Wang, Yasheng Wang, Yitong Li, Lifeng Shang, Kam-Fai Wong, Ruifeng Xu
Abstract
Dialogue models are often enriched with extensive external knowledge to provide informative responses through a retrieval-augmented pipeline. Nevertheless, retrieval-augmented approaches rely on finely annotated retrieval training data and knowledge-grounded response generation data, making it costly to transfer. To tackle this challenge, this paper proposed a retrieval-free approach, KiDG, by automatically turning knowledge documents into simulated multi-turn dialogues through a Multi-Document Traversal algorithm. The simulated knowledge-intensive dialogues constructed by KiDG in one domain can be easily used to train and enhance pre-trained dialogue models’ knowledge w.r.t. this domain without costly annotation. We conduct extensive experiments comparing retrieval-augmented models and a variety of retrieval-free models. We found that dialogue models enhanced with data simulated with KiDG largely outperform state-of-the-art retrieval-free methods, and it achieves comparable performance compared to retrieval-augmented methods while being better, and cheaper at domain transfer.- Anthology ID:
- 2023.acl-long.364
- Original:
- 2023.acl-long.364v1
- Version 2:
- 2023.acl-long.364v2
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6608–6619
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.364
- DOI:
- 10.18653/v1/2023.acl-long.364
- Cite (ACL):
- Rui Wang, Jianzhu Bao, Fei Mi, Yi Chen, Hongru Wang, Yasheng Wang, Yitong Li, Lifeng Shang, Kam-Fai Wong, and Ruifeng Xu. 2023. Retrieval-free Knowledge Injection through Multi-Document Traversal for Dialogue Models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6608–6619, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Retrieval-free Knowledge Injection through Multi-Document Traversal for Dialogue Models (Wang et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/add_acl24_videos/2023.acl-long.364.pdf