Syntactically Diverse Adversarial Network for Knowledge-Grounded Conversation Generation

Fuwei Cui, Hui Di, Hongjie Ren, Kazushige Ouchi, Ze Liu, Jinan Xu


Abstract
Generative conversation systems tend to produce meaningless and generic responses, which significantly reduce the user experience. In order to generate informative and diverse responses, recent studies proposed to fuse knowledge to improve informativeness and adopt latent variables to enhance the diversity. However, utilizing latent variables will lead to the inaccuracy of knowledge in the responses, and the dissemination of wrong knowledge will mislead the communicators. To address this problem, we propose a Syntactically Diverse Adversarial Network (SDAN) for knowledge-grounded conversation model. SDAN contains an adversarial hierarchical semantic network to keep the semantic coherence, a knowledge-aware network to attend more related knowledge for improving the informativeness and a syntactic latent variable network to generate syntactically diverse responses. Additionally, in order to increase the controllability of syntax, we adopt adversarial learning to decouple semantic and syntactic representations. Experimental results show that our model can not only generate syntactically diverse and knowledge-accurate responses but also significantly achieve the balance between improving the syntactic diversity and maintaining the knowledge accuracy.
Anthology ID:
2021.findings-emnlp.394
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4620–4630
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.394
DOI:
10.18653/v1/2021.findings-emnlp.394
Bibkey:
Cite (ACL):
Fuwei Cui, Hui Di, Hongjie Ren, Kazushige Ouchi, Ze Liu, and Jinan Xu. 2021. Syntactically Diverse Adversarial Network for Knowledge-Grounded Conversation Generation. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4620–4630, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Syntactically Diverse Adversarial Network for Knowledge-Grounded Conversation Generation (Cui et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.394.pdf
Video:
 https://aclanthology.org/2021.findings-emnlp.394.mp4
Data
KdConv