Skip to main content

Adversarial feature matching for text generation

Publication ,  Journal Article
Zhang, Y; Gan, Z; Fan, K; Chen, Z; Henao, R; Shen, D; Carin, L
Published in: 34th International Conference on Machine Learning, ICML 2017
January 1, 2017

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.

Duke Scholars

Published In

34th International Conference on Machine Learning, ICML 2017

Publication Date

January 1, 2017

Volume

8

Start / End Page

6093 / 6102
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Zhang, Y., Gan, Z., Fan, K., Chen, Z., Henao, R., Shen, D., & Carin, L. (2017). Adversarial feature matching for text generation. 34th International Conference on Machine Learning, ICML 2017, 8, 6093–6102.
Zhang, Y., Z. Gan, K. Fan, Z. Chen, R. Henao, D. Shen, and L. Carin. “Adversarial feature matching for text generation.” 34th International Conference on Machine Learning, ICML 2017 8 (January 1, 2017): 6093–6102.
Zhang Y, Gan Z, Fan K, Chen Z, Henao R, Shen D, et al. Adversarial feature matching for text generation. 34th International Conference on Machine Learning, ICML 2017. 2017 Jan 1;8:6093–102.
Zhang, Y., et al. “Adversarial feature matching for text generation.” 34th International Conference on Machine Learning, ICML 2017, vol. 8, Jan. 2017, pp. 6093–102.
Zhang Y, Gan Z, Fan K, Chen Z, Henao R, Shen D, Carin L. Adversarial feature matching for text generation. 34th International Conference on Machine Learning, ICML 2017. 2017 Jan 1;8:6093–6102.

Published In

34th International Conference on Machine Learning, ICML 2017

Publication Date

January 1, 2017

Volume

8

Start / End Page

6093 / 6102