@inproceedings{huang-etal-2020-semi,
    title = "Semi-Supervised Dialogue Policy Learning via Stochastic Reward Estimation",
    author = "Huang, Xinting  and
      Qi, Jianzhong  and
      Sun, Yu  and
      Zhang, Rui",
    editor = "Jurafsky, Dan  and
      Chai, Joyce  and
      Schluter, Natalie  and
      Tetreault, Joel",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
    month = jul,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2020.acl-main.62/",
    doi = "10.18653/v1/2020.acl-main.62",
    pages = "660--670"
}