@inproceedings{pachinger-etal-2024-austrotox,
    title = "{A}ustro{T}ox: A Dataset for Target-Based {A}ustrian {G}erman Offensive Language Detection",
    author = "Pachinger, Pia  and
      Goldzycher, Janis  and
      Planitzer, Anna  and
      Kusa, Wojciech  and
      Hanbury, Allan  and
      Neidhardt, Julia",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.findings-acl.713/",
    doi = "10.18653/v1/2024.findings-acl.713",
    pages = "11990--12001",
    abstract = "Model interpretability in toxicity detection greatly profits from token-level annotations. However, currently, such annotations are only available in English. We introduce a dataset annotated for offensive language detection sourced from a news forum, notable for its incorporation of the Austrian German dialect, comprising 4,562 user comments. In addition to binary offensiveness classification, we identify spans within each comment constituting vulgar language or representing targets of offensive statements. We evaluate fine-tuned Transformer models as well as large language models in a zero- and few-shot fashion. The results indicate that while fine-tuned models excel in detecting linguistic peculiarities such as vulgar dialect, large language models demonstrate superior performance in detecting offensiveness in AustroTox."
}