@inproceedings{glavas-etal-2020-xhate,
    title = "{XH}ate-999: Analyzing and Detecting Abusive Language Across Domains and Languages",
    author = "Glava{\v{s}}, Goran  and
      Karan, Vanja Mladen  and
      Vuli{\'c}, Ivan",
    editor = "Scott, Donia  and
      Bel, Nuria  and
      Zong, Chengqing",
    booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "International Committee on Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2020.coling-main.559/",
    doi = "10.18653/v1/2020.coling-main.559",
    pages = "6350--6365",
    abstract = "We present XHate-999, a multi-domain and multilingual evaluation data set for abusive language detection. By aligning test instances across six typologically diverse languages, XHate-999 for the first time allows for disentanglement of the domain transfer and language transfer effects in abusive language detection. We conduct a series of domain- and language-transfer experiments with state-of-the-art monolingual and multilingual transformer models, setting strong baseline results and profiling XHate-999 as a comprehensive evaluation resource for abusive language detection. Finally, we show that domain- and language-adaption, via intermediate masked language modeling on abusive corpora in the target language, can lead to substantially improved abusive language detection in the target language in the zero-shot transfer setups."
}