@inproceedings{wang-2018-interpreting,
    title = "Interpreting Neural Network Hate Speech Classifiers",
    author = "Wang, Cindy",
    editor = "Fi{\v{s}}er, Darja  and
      Huang, Ruihong  and
      Prabhakaran, Vinodkumar  and
      Voigt, Rob  and
      Waseem, Zeerak  and
      Wernimont, Jacqueline",
    booktitle = "Proceedings of the 2nd Workshop on Abusive Language Online ({ALW}2)",
    month = oct,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/W18-5111/",
    doi = "10.18653/v1/W18-5111",
    pages = "86--92"
}