Reciprocal Learning of Knowledge Retriever and Response Ranker for Knowledge-Grounded Conversations

Jiazhan Feng, Chongyang Tao, Zhen Li, Chang Liu, Tao Shen, Dongyan Zhao


Abstract
Grounding dialogue agents with knowledge documents has sparked increased attention in both academia and industry. Recently, a growing body of work is trying to build retrieval-based knowledge-grounded dialogue systems. While promising, these approaches require collecting pairs of dialogue context and the corresponding ground-truth knowledge sentences that contain the information regarding the dialogue context. Unfortunately, hand-labeling data to that end is time-consuming, and many datasets and applications lack such knowledge annotations. In this paper, we propose a reciprocal learning approach to jointly optimize a knowledge retriever and a response ranker for knowledge-grounded response retrieval without ground-truth knowledge labels. Specifically, the knowledge retriever uses the feedback from the response ranker as pseudo supervised signals of knowledge retrieval for updating its parameters, while the response ranker also receives the top-ranked knowledge sentences from knowledge retriever for optimization. Evaluation results on two public benchmarks show that our model can significantly outperform previous state-of-the-art methods.
Anthology ID:
2022.coling-1.31
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
389–399
Language:
URL:
https://aclanthology.org/2022.coling-1.31
DOI:
Bibkey:
Cite (ACL):
Jiazhan Feng, Chongyang Tao, Zhen Li, Chang Liu, Tao Shen, and Dongyan Zhao. 2022. Reciprocal Learning of Knowledge Retriever and Response Ranker for Knowledge-Grounded Conversations. In Proceedings of the 29th International Conference on Computational Linguistics, pages 389–399, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Reciprocal Learning of Knowledge Retriever and Response Ranker for Knowledge-Grounded Conversations (Feng et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.31.pdf
Data
Wizard of Wikipedia