A Discrete CVAE for Response Generation on Short-Text Conversation

Jun Gao, Wei Bi, Xiaojiang Liu, Junhui Li, Guodong Zhou, Shuming Shi


Abstract
Neural conversation models such as encoder-decoder models are easy to generate bland and generic responses. Some researchers propose to use the conditional variational autoencoder (CVAE) which maximizes the lower bound on the conditional log-likelihood on a continuous latent variable. With different sampled latent variables, the model is expected to generate diverse responses. Although the CVAE-based models have shown tremendous potential, their improvement of generating high-quality responses is still unsatisfactory. In this paper, we introduce a discrete latent variable with an explicit semantic meaning to improve the CVAE on short-text conversation. A major advantage of our model is that we can exploit the semantic distance between the latent variables to maintain good diversity between the sampled latent variables. Accordingly, we propose a two-stage sampling approach to enable efficient diverse variable selection from a large latent space assumed in the short-text conversation task. Experimental results indicate that our model outperforms various kinds of generation models under both automatic and human evaluations and generates more diverse and informative responses.
Anthology ID:
D19-1198
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1898–1908
Language:
URL:
https://aclanthology.org/D19-1198
DOI:
10.18653/v1/D19-1198
Bibkey:
Cite (ACL):
Jun Gao, Wei Bi, Xiaojiang Liu, Junhui Li, Guodong Zhou, and Shuming Shi. 2019. A Discrete CVAE for Response Generation on Short-Text Conversation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1898–1908, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
A Discrete CVAE for Response Generation on Short-Text Conversation (Gao et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp22-frontmatter/D19-1198.pdf