@inproceedings{yuan-etal-2022-separating,
    title = "Separating Hate Speech and Offensive Language Classes via Adversarial Debiasing",
    author = {Yuan, Shuzhou  and
      Maronikolakis, Antonis  and
      Sch{\"u}tze, Hinrich},
    booktitle = "Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)",
    month = jul,
    year = "2022",
    address = "Seattle, Washington (Hybrid)",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.woah-1.1",
    doi = "10.18653/v1/2022.woah-1.1",
    pages = "1--10",
    abstract = "Research to tackle hate speech plaguing online media has made strides in providing solutions, analyzing bias and curating data. A challenging problem is ambiguity between hate speech and offensive language, causing low performance both overall and specifically for the hate speech class. It can be argued that misclassifying actual hate speech content as merely offensive can lead to further harm against targeted groups. In our work, we mitigate this potentially harmful phenomenon by proposing an adversarial debiasing method to separate the two classes. We show that our method works for English, Arabic German and Hindi, plus in a multilingual setting, improving performance over baselines.",
}