@inproceedings{chen2018adversarial,
author = {Chen, Liqun and Dai, Shuyang and Tao, Chenyang and Shen, Dinghan and Gan, Zhe and Zhang, Haichao and Zhang, Yizhe and Carin, Lawrence},
title = {Adversarial Text Generation via Feature-Mover's Distance},
booktitle = {NIPS 2018},
year = {2018},
month = {December},
abstract = {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.},
url = {http://approjects.co.za/?big=en-us/research/publication/adversarial-text-generation-via-feature-movers-distance/},
}