Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders

Tiancheng Zhao, Ran Zhao, Maxine Eskenazi


Abstract
While recent neural encoder-decoder models have shown great promise in modeling open-domain conversations, they often generate dull and generic responses. Unlike past work that has focused on diversifying the output of the decoder from word-level to alleviate this problem, we present a novel framework based on conditional variational autoencoders that capture the discourse-level diversity in the encoder. Our model uses latent variables to learn a distribution over potential conversational intents and generates diverse responses using only greedy decoders. We have further developed a novel variant that is integrated with linguistic prior knowledge for better performance. Finally, the training procedure is improved through introducing a bag-of-word loss. Our proposed models have been validated to generate significantly more diverse responses than baseline approaches and exhibit competence of discourse-level decision-making.
Anthology ID:
P17-1061
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Editors:
Regina Barzilay, Min-Yen Kan
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
654–664
Language:
URL:
https://aclanthology.org/P17-1061
DOI:
10.18653/v1/P17-1061
Bibkey:
Cite (ACL):
Tiancheng Zhao, Ran Zhao, and Maxine Eskenazi. 2017. Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 654–664, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders (Zhao et al., ACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/P17-1061.pdf
Presentation:
 P17-1061.Presentation.pdf
Dataset:
 P17-1061.Datasets.zip
Video:
 https://aclanthology.org/P17-1061.mp4
Code
 snakeztc/NeuralDialog-CVAE
Data
DailyDialogSwitchboard-1 Corpus