Poster
Adversarial Text Generation via Feature-Mover's Distance
Liqun Chen · Shuyang Dai · Chenyang Tao · Haichao Zhang · Zhe Gan · Dinghan Shen · Yizhe Zhang · Guoyin Wang · Dinghan Shen · Lawrence Carin

Wed Dec 5th 10:45 AM -- 12:45 PM @ Room 517 AB #129

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.

Author Information

Liqun Chen (Duke University)
Shuyang Dai (Duke University)
Chenyang Tao (Duke University)
Haichao Zhang (Baidu Research)
Zhe Gan (Microsoft)
Dinghan Shen (Duke University)
Yizhe Zhang (Microsoft Research)
Guoyin Wang (Duke University)
Dinghan Shen (Duke University)
Lawrence Carin (Duke University)

More from the Same Authors