@inproceedings{khandelwal-2021-weasul,
    title = "{W}ea{S}u{L}: Weakly Supervised Dialogue Policy Learning: Reward Estimation for Multi-turn Dialogue",
    author = "Khandelwal, Anant",
    editor = "Feng, Song  and
      Reddy, Siva  and
      Alikhani, Malihe  and
      He, He  and
      Ji, Yangfeng  and
      Iyyer, Mohit  and
      Yu, Zhou",
    booktitle = "Proceedings of the 1st Workshop on Document-grounded Dialogue and Conversational Question Answering (DialDoc 2021)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.dialdoc-1.10/",
    doi = "10.18653/v1/2021.dialdoc-1.10",
    pages = "69--80"
}