Dialogue Generation with GAN

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.

Cite

Text

Su et al. "Dialogue Generation with GAN." AAAI Conference on Artificial Intelligence, 2018. doi:10.1609/AAAI.V32I1.12158

Markdown

[Su et al. "Dialogue Generation with GAN." AAAI Conference on Artificial Intelligence, 2018.](https://mlanthology.org/aaai/2018/su2018aaai-dialogue/) doi:10.1609/AAAI.V32I1.12158

BibTeX

@inproceedings{su2018aaai-dialogue,
  title     = {{Dialogue Generation with GAN}},
  author    = {Su, Hui and Shen, Xiaoyu and Hu, Pengwei and Li, Wenjie and Chen, Yun},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2018},
  pages     = {8163-8164},
  doi       = {10.1609/AAAI.V32I1.12158},
  url       = {https://mlanthology.org/aaai/2018/su2018aaai-dialogue/}
}