Papers Published

1. Dai, S; Gan, Z; Cheng, Y; Tao, C; Carin, L; Liu, J, APo-VAE: Text Generation in Hyperbolic Space, NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference (January, 2021), pp. 416-431 .
   (last updated on 2024/12/31)

   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. We investigate text generation in a hyperbolic latent space to learn continuous hierarchical representations. An Adversarial Poincaré Variational Autoencoder (APo-VAE) is presented, where both the prior and variational posterior of latent variables are defined over a Poincaré 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.