@inproceedings{henrichsen-rathje-2020-smatgrisene,
    title = "Smatgrisene at {S}em{E}val-2020 Task 12: Offense Detection by {AI} - with a Pinch of Real {I}",
    author = "Henrichsen, Peter Juel  and
      Rathje, Marianne",
    editor = "Herbelot, Aurelie  and
      Zhu, Xiaodan  and
      Palmer, Alexis  and
      Schneider, Nathan  and
      May, Jonathan  and
      Shutova, Ekaterina",
    booktitle = "Proceedings of the Fourteenth Workshop on Semantic Evaluation",
    month = dec,
    year = "2020",
    address = "Barcelona (online)",
    publisher = "International Committee for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2020.semeval-1.284/",
    doi = "10.18653/v1/2020.semeval-1.284",
    pages = "2140--2145",
    abstract = "This paper discusses how ML based classifiers can be enhanced disproportionately by adding small amounts of qualitative linguistic knowledge. As an example we present the Danish classifier Smatgrisene, our contribution to the recent OffensEval Challenge 2020. The classifier was trained on 3000 social media posts annotated for offensiveness, supplemented by rules extracted from the reference work on Danish offensive language (Rathje 2014b). Smatgrisene did surprisingly well in the competition in spite of its extremely simple design, showing an interesting trade-off between technological muscle and linguistic intelligence. Finally, we comment on the perspectives in combining qualitative and quantitative methods for NLP."
}