Oral
Adversarially Regularized Autoencoders
Jake Zhao · Yoon Kim · Kelly Zhang · Alexander Rush · Yann LeCun

Fri Jul 13th 10:00 -- 10:10 AM @ A7

Deep latent variable models, trained using variational autoencoders or generative adversarial networks, are now a key technique for representation learning of continuous structures. However, applying similar methods to discrete structures, such as text sequences or discretized images, has proven to be more challenging. In this work, we propose a more flexible method for training deep latent variable models of discrete structures. Our approach is based on the recently proposed Wasserstein Autoencoder (WAE) which formalizes adversarial autoencoders as an optimal transport problem. We first extend this framework to model discrete sequences, and then further explore different learned priors targeting a controllable representation. Unlike many other latent variable generative models for text, this adversarially regularized autoencoder (ARAE) allows us to generate fluent textual outputs as well as perform manipulations in the latent space to induce change in the output space. Finally we show that the latent representation can be trained to perform unaligned textual style transfer, giving improvements both in automatic measures and human evaluation.

Author Information

Jake Zhao (NYU / Facebook AI Research)
Yoon Kim (Harvard University)
Kelly Zhang (New York University)
Alexander Rush (Harvard University)
Yann LeCun (New York University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors