@inproceedings{su-etal-2016-line,
    title = "On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems",
    author = "Su, Pei-Hao  and
      Ga{\v{s}}i{\'c}, Milica  and
      Mrk{\v{s}}i{\'c}, Nikola  and
      Rojas-Barahona, Lina M.  and
      Ultes, Stefan  and
      Vandyke, David  and
      Wen, Tsung-Hsien  and
      Young, Steve",
    editor = "Erk, Katrin  and
      Smith, Noah A.",
    booktitle = "Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2016",
    address = "Berlin, Germany",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/P16-1230/",
    doi = "10.18653/v1/P16-1230",
    pages = "2431--2441"
}