@inproceedings{peng-etal-2017-maximum,
    title = "Maximum Margin Reward Networks for Learning from Explicit and Implicit Supervision",
    author = "Peng, Haoruo  and
      Chang, Ming-Wei  and
      Yih, Wen-tau",
    editor = "Palmer, Martha  and
      Hwa, Rebecca  and
      Riedel, Sebastian",
    booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",
    month = sep,
    year = "2017",
    address = "Copenhagen, Denmark",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/D17-1252/",
    doi = "10.18653/v1/D17-1252",
    pages = "2368--2378"
}