@inproceedings{caselli-van-der-veen-2023-benchmarking,
    title = "Benchmarking Offensive and Abusive Language in {D}utch Tweets",
    author = "Caselli, Tommaso  and
      Van Der Veen, Hylke",
    editor = "Chung, Yi-ling  and
      R{\{}{\textbackslash}{''}ottger{\}}, Paul  and
      Nozza, Debora  and
      Talat, Zeerak  and
      Mostafazadeh Davani, Aida",
    booktitle = "The 7th Workshop on Online Abuse and Harms (WOAH)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2023.woah-1.7/",
    doi = "10.18653/v1/2023.woah-1.7",
    pages = "69--84",
    abstract = "We present an extensive evaluation of different fine-tuned models to detect instances of offensive and abusive language in Dutch across three benchmarks: a standard held-out test, a task- agnostic functional benchmark, and a dynamic test set. We also investigate the use of data cartography to identify high quality training data. Our results show a relatively good quality of the manually annotated data used to train the models while highlighting some critical weakness. We have also found a good portability of trained models along the same language phenomena. As for the data cartography, we have found a positive impact only on the functional benchmark and when selecting data per annotated dimension rather than using the entire training material."
}