Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems

Yicheng Zou, Zhihua Liu, Xingwu Hu, Qi Zhang


Abstract
Human dialogue contains evolving concepts, and speakers naturally associate multiple concepts to compose a response. However, current dialogue models with the seq2seq framework lack the ability to effectively manage concept transitions and can hardly introduce multiple concepts to responses in a sequential decoding manner. To facilitate a controllable and coherent dialogue, in this work, we devise a concept-guided non-autoregressive model (CG-nAR) for open-domain dialogue generation. The proposed model comprises a multi-concept planning module that learns to identify multiple associated concepts from a concept graph and a customized Insertion Transformer that performs concept-guided non-autoregressive generation to complete a response. The experimental results on two public datasets show that CG-nAR can produce diverse and coherent responses, outperforming state-of-the-art baselines in both automatic and human evaluations with substantially faster inference speed.
Anthology ID:
2021.emnlp-main.169
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2215–2226
Language:
URL:
https://aclanthology.org/2021.emnlp-main.169
DOI:
10.18653/v1/2021.emnlp-main.169
Bibkey:
Cite (ACL):
Yicheng Zou, Zhihua Liu, Xingwu Hu, and Qi Zhang. 2021. Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2215–2226, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems (Zou et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.169.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.169.mp4
Code
 rowitzou/cg-nar