Knowledge-Grounded Dialogue Generation with Pre-trained Language Models

Xueliang Zhao, Wei Wu, Can Xu, Chongyang Tao, Dongyan Zhao, Rui Yan


Abstract
We study knowledge-grounded dialogue generation with pre-trained language models. To leverage the redundant external knowledge under capacity constraint, we propose equipping response generation defined by a pre-trained language model with a knowledge selection module, and an unsupervised approach to jointly optimizing knowledge selection and response generation with unlabeled dialogues. Empirical results on two benchmarks indicate that our model can significantly outperform state-of-the-art methods in both automatic evaluation and human judgment.
Anthology ID:
2020.emnlp-main.272
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3377–3390
Language:
URL:
https://aclanthology.org/2020.emnlp-main.272
DOI:
10.18653/v1/2020.emnlp-main.272
Bibkey:
Cite (ACL):
Xueliang Zhao, Wei Wu, Can Xu, Chongyang Tao, Dongyan Zhao, and Rui Yan. 2020. Knowledge-Grounded Dialogue Generation with Pre-trained Language Models. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3377–3390, Online. Association for Computational Linguistics.
Cite (Informal):
Knowledge-Grounded Dialogue Generation with Pre-trained Language Models (Zhao et al., EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2020.emnlp-main.272.pdf
Video:
 https://slideslive.com/38938823
Code
 zhaoxlpku/KnowledGPT
Data
CMU DoGWizard of Wikipedia