@inproceedings{nguyen-etal-2017-reinforcement,
    title = "Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback",
    author = "Nguyen, Khanh  and
      Daum{\'e} III, Hal  and
      Boyd-Graber, Jordan",
    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/D17-1153/",
    doi = "10.18653/v1/D17-1153",
    pages = "1464--1474"
}