@inproceedings{xu-etal-2018-diversity,
    title = "Diversity-Promoting {GAN}: A Cross-Entropy Based Generative Adversarial Network for Diversified Text Generation",
    author = "Xu, Jingjing  and
      Ren, Xuancheng  and
      Lin, Junyang  and
      Sun, Xu",
    editor = "Riloff, Ellen  and
      Chiang, David  and
      Hockenmaier, Julia  and
      Tsujii, Jun{'}ichi",
    booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
    month = oct # "-" # nov,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/D18-1428/",
    doi = "10.18653/v1/D18-1428",
    pages = "3940--3949",
    abstract = "Existing text generation methods tend to produce repeated and ``boring'' expressions. To tackle this problem, we propose a new text generation model, called Diversity-Promoting Generative Adversarial Network (DP-GAN). The proposed model assigns low reward for repeatedly generated text and high reward for ``novel'' and fluent text, encouraging the generator to produce diverse and informative text. Moreover, we propose a novel language-model based discriminator, which can better distinguish novel text from repeated text without the saturation problem compared with existing classifier-based discriminators. The experimental results on review generation and dialogue generation tasks demonstrate that our model can generate substantially more diverse and informative text than existing baselines."
}