2017 AdversarialFeatureMatchingforTe

• (Zhang, Gan et al., 2017) ⇒ Yizhe Zhang, Zhe Gan, Kai Fan, Zhi Chen, Ricardo Henao, Dinghan Shen, and Lawrence Carin. (2017). “Adversarial Feature Matching for Text Generation". In: Proceedings of the 34th International Conference on Machine Learning (ICML 2017).

Subject Headings: Adversarial Feature Matching For Text Generation (TextGAN).

Notes

• Other Version(s) and Link(s):
  • PMRL: http://proceedings.mlr.press/v70/zhang17b.html
  • DBLP: https://dblp.org/rec/conf/icml/ZhangGFCHSC17
  • ArXiv: https://arxiv.org/abs/1706.03850

Cited By

• Google Scholar: ~ 162 Citations.
• Semantic Scholar: ~ 149 Citations.
• MS Academic: ~ 150 Citations.

Quotes

Abstract

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.

BibTex

@inproceedings{2017_AdversarialFeatureMatchingforTe,
  author    = {Yizhe Zhang and
               Zhe Gan and
               Kai Fan and
               Zhi Chen and
               Ricardo Henao and
               Dinghan Shen and
               Lawrence Carin},
  editor    = {Doina Precup and
               Yee Whye Teh},
  title     = {Adversarial Feature Matching for Text Generation},
  booktitle = {Proceedings of the 34th International Conference on Machine Learning (ICML 2017),
               Sydney, NSW, Australia, 6-11 August 2017},
  series    = {Proceedings of Machine Learning Research},
  volume    = {70},
  pages     = {4006--4015},
  publisher = {PMLR},
  year      = {2017},
  url       = {http://proceedings.mlr.press/v70/zhang17b.html},
}

---

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2017 AdversarialFeatureMatchingforTe	Lawrence Carin Kai Fan Yizhe Zhang Zhe Gan Zhi Chen Ricardo Henao Dinghan Shen			Adversarial Feature Matching for Text Generation						2017