Stochastic Wasserstein Autoencoder for Probabilistic Sentence Generation

Hareesh Bahuleyan, Lili Mou, Hao Zhou, Olga Vechtomova

[How to correct problems with metadata yourself]


Abstract
The variational autoencoder (VAE) imposes a probabilistic distribution (typically Gaussian) on the latent space and penalizes the Kullback-Leibler (KL) divergence between the posterior and prior. In NLP, VAEs are extremely difficult to train due to the problem of KL collapsing to zero. One has to implement various heuristics such as KL weight annealing and word dropout in a carefully engineered manner to successfully train a VAE for text. In this paper, we propose to use the Wasserstein autoencoder (WAE) for probabilistic sentence generation, where the encoder could be either stochastic or deterministic. We show theoretically and empirically that, in the original WAE, the stochastically encoded Gaussian distribution tends to become a Dirac-delta function, and we propose a variant of WAE that encourages the stochasticity of the encoder. Experimental results show that the latent space learned by WAE exhibits properties of continuity and smoothness as in VAEs, while simultaneously achieving much higher BLEU scores for sentence reconstruction.
Anthology ID:
N19-1411
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4068–4076
Language:
URL:
https://aclanthology.org/N19-1411
DOI:
10.18653/v1/N19-1411
Bibkey:
Cite (ACL):
Hareesh Bahuleyan, Lili Mou, Hao Zhou, and Olga Vechtomova. 2019. Stochastic Wasserstein Autoencoder for Probabilistic Sentence Generation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4068–4076, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Stochastic Wasserstein Autoencoder for Probabilistic Sentence Generation (Bahuleyan et al., NAACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/teach-a-man-to-fish/N19-1411.pdf
Video:
 https://preview.aclanthology.org/teach-a-man-to-fish/N19-1411.mp4
Code
 HareeshBahuleyan/probabilistic_nlg
Data
DailyDialogSNLI