Generating Relevant and Coherent Dialogue Responses using Self-Separated Conditional Variational AutoEncoders

Bin Sun, Shaoxiong Feng, Yiwei Li, Jiamou Liu, Kan Li


Abstract
Conditional Variational AutoEncoder (CVAE) effectively increases the diversity and informativeness of responses in open-ended dialogue generation tasks through enriching the context vector with sampled latent variables. However, due to the inherent one-to-many and many-to-one phenomena in human dialogues, the sampled latent variables may not correctly reflect the contexts’ semantics, leading to irrelevant and incoherent generated responses. To resolve this problem, we propose Self-separated Conditional Variational AutoEncoder (abbreviated as SepaCVAE) that introduces group information to regularize the latent variables, which enhances CVAE by improving the responses’ relevance and coherence while maintaining their diversity and informativeness. SepaCVAE actively divides the input data into groups, and then widens the absolute difference between data pairs from distinct groups, while narrowing the relative distance between data pairs in the same group. Empirical results from automatic evaluation and detailed analysis demonstrate that SepaCVAE can significantly boost responses in well-established open-domain dialogue datasets.
Anthology ID:
2021.acl-long.437
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5624–5637
Language:
URL:
https://aclanthology.org/2021.acl-long.437
DOI:
10.18653/v1/2021.acl-long.437
Bibkey:
Cite (ACL):
Bin Sun, Shaoxiong Feng, Yiwei Li, Jiamou Liu, and Kan Li. 2021. Generating Relevant and Coherent Dialogue Responses using Self-Separated Conditional Variational AutoEncoders. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 5624–5637, Online. Association for Computational Linguistics.
Cite (Informal):
Generating Relevant and Coherent Dialogue Responses using Self-Separated Conditional Variational AutoEncoders (Sun et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.437.pdf
Video:
 https://aclanthology.org/2021.acl-long.437.mp4
Data
DailyDialog