Adversarial text generation via feature-mover's distance

Published

Conference Paper

© 2018 Curran Associates Inc..All rights reserved. Generative adversarial networks (GANs) have achieved significant success in generating real-valued data. However, the discrete nature of text hinders the application of GAN to text-generation tasks. Instead of using the standard GAN objective, we propose to improve text-generation GAN via a novel approach inspired by optimal transport. Specifically, we consider matching the latent feature distributions of real and synthetic sentences using a novel metric, termed the feature-mover's distance (FMD). This formulation leads to a highly discriminative critic and easy-to-optimize objective, overcoming the mode-collapsing and brittle-training problems in existing methods. Extensive experiments are conducted on a variety of tasks to evaluate the proposed model empirically, including unconditional text generation, style transfer from non-parallel text, and unsupervised cipher cracking. The proposed model yields superior performance, demonstrating wide applicability and effectiveness.

Duke Authors

Cited Authors

  • Chen, L; Dai, S; Tao, C; Shen, D; Gan, Z; Zhang, H; Zhang, Y; Carin, L

Published Date

  • January 1, 2018

Published In

Volume / Issue

  • 2018-December /

Start / End Page

  • 4666 - 4677

International Standard Serial Number (ISSN)

  • 1049-5258

Citation Source

  • Scopus