Year: 2020
Type: preprint
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 KL divergence, an adversarial learning procedure is introduced to empower robust model training. Extensive experiments in language modeling and dialog-response generation tasks demonstrate the winning 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.
Source: arXiv (Cornell University)
Authors: Dai, Shuyang, Gan, Zhe, Cheng, Yu, Tao, Chenyang, Carin, Lawrence, Liu, Jingjing
Institutions: Duke University, Microsoft (United States)
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3021132617