The Generative Adversarial Network (GAN) has achieved great success in generating realistic (real-valued) synthetic data. However, convergence issues and difficulties dealing with discrete data hinder the applicability of GAN to text. We propose a framework for generating realistic text via adversarial training. We employ a long short-term memory network as generator, and a convolutional network as discriminator. Instead of using the standard objective of GAN, we propose matching the high-dimensional latent feature distributions of real and synthetic sentences, via a kernelized discrepancy metric. This eases adversarial training by alleviating the mode-collapsing problem. Our experiments show superior performance in quantitative evaluation, and demonstrate that our model can generate realistic-looking sentences.
@article{arxiv.1706.03850,
title = {Adversarial Feature Matching for Text Generation},
author = {Yizhe Zhang and Zhe Gan and Kai Fan and Zhi Chen and Ricardo Henao and Dinghan Shen and Lawrence Carin},
journal= {arXiv preprint arXiv:1706.03850},
year = {2017}
}