There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference Learning

Xueliang Zhao, Tingchen Fu, Chongyang Tao, Rui Yan


Abstract
Knowledge-grounded dialogue (KGC) shows excellent potential to deliver an engaging and informative response. However, existing approaches emphasize selecting one golden knowledge given a particular dialogue context, overlooking the one-to-many phenomenon in dialogue. As a result, existing paradigm limits the diversity of knowledge selection and generation. To this end, we establish a multi-reference KGC dataset and propose a series of metrics to systematically assess the one-to-many efficacy of existing KGC models. Furthermore, to extend the hypothesis space of knowledge selection to enhance the mapping relationship between multiple knowledge and multiple responses, we devise a span-based variational model and optimize the model in a wake-sleep style with an ameliorated evidence lower bound objective to learn the one-to-many generalization. Both automatic and human evaluations demonstrate the efficacy of our approach.
Anthology ID:
2022.emnlp-main.123
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1878–1891
Language:
URL:
https://aclanthology.org/2022.emnlp-main.123
DOI:
10.18653/v1/2022.emnlp-main.123
Bibkey:
Cite (ACL):
Xueliang Zhao, Tingchen Fu, Chongyang Tao, and Rui Yan. 2022. There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference Learning. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 1878–1891, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference Learning (Zhao et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-2023-videos/2022.emnlp-main.123.pdf