@inproceedings{chapman-etal-2020-coli,
    title = "{C}o{L}i at {U}d{S} at {S}em{E}val-2020 Task 12: Offensive Tweet Detection with Ensembling",
    author = "Chapman, Kathryn  and
      Bernhard, Johannes  and
      Klakow, Dietrich",
    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/ingest-emnlp/2020.semeval-1.252/",
    doi = "10.18653/v1/2020.semeval-1.252",
    pages = "1916--1924",
    abstract = "We present our submission and results for SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020) where we participated in offensive tweet classification tasks in English, Arabic, Greek, Turkish and Danish. Our approach included classical machine learning architectures such as support vector machines and logistic regression combined in an ensemble with a multilingual transformer-based model (XLM-R). The transformer model is trained on all languages combined in order to create a fully multilingual model which can leverage knowledge between languages. The machine learning model hyperparameters are fine-tuned and the statistically best performing ones included in the final ensemble."
}