@inproceedings{pasunuru-etal-2020-dorb,
    title = "{DORB}: Dynamically Optimizing Multiple Rewards with Bandits",
    author = "Pasunuru, Ramakanth  and
      Guo, Han  and
      Bansal, Mohit",
    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.625/",
    doi = "10.18653/v1/2020.emnlp-main.625",
    pages = "7766--7780"
}