Talk
Adversarial Feature Matching for Text Generation
Yizhe Zhang · Zhe Gan · Kai Fan · Zhi Chen · Ricardo Henao · Dinghan Shen · Lawrence Carin

Wed Aug 9th 02:42 -- 03:00 PM @ Parkside 1

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.

Author Information

Yizhe Zhang (Duke university)
Zhe Gan (Duke University)
Kai Fan
Zhi Chen (Nanjing University)
Ricardo Henao (Duke University)
Dinghan Shen (Duke University)
Lawrence Carin (Duke)

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

More from the Same Authors