Multi-Grained Knowledge Retrieval for End-to-End Task-Oriented Dialog

Fanqi Wan, Weizhou Shen, Ke Yang, Xiaojun Quan, Wei Bi


Abstract
Retrieving proper domain knowledge from an external database lies at the heart of end-to-end task-oriented dialog systems to generate informative responses. Most existing systems blend knowledge retrieval with response generation and optimize them with direct supervision from reference responses, leading to suboptimal retrieval performance when the knowledge base becomes large-scale. To address this, we propose to decouple knowledge retrieval from response generation and introduce a multi-grained knowledge retriever (MAKER) that includes an entity selector to search for relevant entities and an attribute selector to filter out irrelevant attributes. To train the retriever, we propose a novel distillation objective that derives supervision signals from the response generator. Experiments conducted on three standard benchmarks with both small and large-scale knowledge bases demonstrate that our retriever performs knowledge retrieval more effectively than existing methods. Our code has been made publicly available at https://github.com/18907305772/MAKER.
Anthology ID:
2023.acl-long.627
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:
11196–11210
Language:
URL:
https://aclanthology.org/2023.acl-long.627
DOI:
10.18653/v1/2023.acl-long.627
Bibkey:
Cite (ACL):
Fanqi Wan, Weizhou Shen, Ke Yang, Xiaojun Quan, and Wei Bi. 2023. Multi-Grained Knowledge Retrieval for End-to-End Task-Oriented Dialog. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11196–11210, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Multi-Grained Knowledge Retrieval for End-to-End Task-Oriented Dialog (Wan et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2023.acl-long.627.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-4/2023.acl-long.627.mp4