Dual-Feedback Knowledge Retrieval for Task-Oriented Dialogue Systems
Tianyuan Shi, Liangzhi Li, Zijian Lin, Tao Yang, Xiaojun Quan, Qifan Wang
Abstract
Efficient knowledge retrieval plays a pivotal role in ensuring the success of end-to-end task-oriented dialogue systems by facilitating the selection of relevant information necessary to fulfill user requests. However, current approaches generally integrate knowledge retrieval and response generation, which poses scalability challenges when dealing with extensive knowledge bases. Taking inspiration from open-domain question answering, we propose a retriever-generator architecture that harnesses a retriever to retrieve pertinent knowledge and a generator to generate system responses. Due to the lack of retriever training labels, we propose relying on feedback from the generator as pseudo-labels to train the retriever. To achieve this, we introduce a dual-feedback mechanism that generates both positive and negative feedback based on the output of the generator. Our method demonstrates superior performance in task-oriented dialogue tasks, as evidenced by experimental results on three benchmark datasets.- Anthology ID:
- 2023.emnlp-main.405
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6566–6580
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.405
- DOI:
- 10.18653/v1/2023.emnlp-main.405
- Cite (ACL):
- Tianyuan Shi, Liangzhi Li, Zijian Lin, Tao Yang, Xiaojun Quan, and Qifan Wang. 2023. Dual-Feedback Knowledge Retrieval for Task-Oriented Dialogue Systems. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 6566–6580, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Dual-Feedback Knowledge Retrieval for Task-Oriented Dialogue Systems (Shi et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/corrections-2024-05/2023.emnlp-main.405.pdf