@inproceedings{zhu-etal-2020-counterfactual,
    title = "Counterfactual Off-Policy Training for Neural Dialogue Generation",
    author = "Zhu, Qingfu  and
      Zhang, Wei-Nan  and
      Liu, Ting  and
      Wang, William Yang",
    editor = "Webber, Bonnie  and
      Cohn, Trevor  and
      He, Yulan  and
      Liu, Yang",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2020.emnlp-main.276/",
    doi = "10.18653/v1/2020.emnlp-main.276",
    pages = "3438--3448"
}