Dialogue Generation With GAN

Authors

  • Hui Su The Hong Kong Polytechnic University
  • Xiaoyu Shen Max Planck Institute Informatics
  • Pengwei Hu The Hong Kong Polytechnic University
  • Wenjie Li The Hong Kong Polytechnic University
  • Yun Chen The University of Hong Kong

Abstract

This paper presents a Generative Adversarial Network (GAN) to model multiturn dialogue generation, which trains a latent hierarchical recurrent encoder-decoder simultaneously with a discriminative classifier that make the prior approximate to the posterior. Experiments show that our model achieves better results.

Downloads

Published

2018-04-29

How to Cite

Su, H., Shen, X., Hu, P., Li, W., & Chen, Y. (2018). Dialogue Generation With GAN. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/12158