APo-VAE: Text Generation in Hyperbolic Space

Shuyang Dai, Zhe Gan, Yu Cheng, Chenyang Tao, Lawrence Carin, Jingjing Liu


Abstract
Natural language often exhibits inherent hierarchical structure ingrained with complex syntax and semantics. However, most state-of-the-art deep generative models learn embeddings only in Euclidean vector space, without accounting for this structural property of language. In this paper, we investigate text generation in a hyperbolic latent space to learn continuous hierarchical representations. An Adversarial Poincare Variational Autoencoder (APo-VAE) is presented, where both the prior and variational posterior of latent variables are defined over a Poincare ball via wrapped normal distributions. By adopting the primal-dual formulation of Kullback-Leibler divergence, an adversarial learning procedure is introduced to empower robust model training. Extensive experiments in language modeling, unaligned style transfer, and dialog-response generation demonstrate the effectiveness of the proposed APo-VAE model over VAEs in Euclidean latent space, thanks to its superb capabilities in capturing latent language hierarchies in hyperbolic space.
Anthology ID:
2021.naacl-main.36
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
416–431
Language:
URL:
https://aclanthology.org/2021.naacl-main.36
DOI:
10.18653/v1/2021.naacl-main.36
Bibkey:
Cite (ACL):
Shuyang Dai, Zhe Gan, Yu Cheng, Chenyang Tao, Lawrence Carin, and Jingjing Liu. 2021. APo-VAE: Text Generation in Hyperbolic Space. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 416–431, Online. Association for Computational Linguistics.
Cite (Informal):
APo-VAE: Text Generation in Hyperbolic Space (Dai et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.36.pdf
Data
Penn Treebank