@inproceedings{ghadery-moens-2020-liir,
    title = "{LIIR} at {S}em{E}val-2020 Task 12: A Cross-Lingual Augmentation Approach for Multilingual Offensive Language Identification",
    author = "Ghadery, Erfan  and
      Moens, Marie-Francine",
    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/jlcl-multiple-ingestion/2020.semeval-1.274/",
    doi = "10.18653/v1/2020.semeval-1.274",
    pages = "2073--2079",
    abstract = "This paper presents our system entitled {\textquoteleft}LIIR' for SemEval-2020 Task 12 on Multilingual Offensive Language Identification in Social Media (OffensEval 2). We have participated in sub-task A for English, Danish, Greek, Arabic, and Turkish languages. We adapt and fine-tune the BERT and Multilingual Bert models made available by Google AI for English and non-English languages respectively. For the English language, we use a combination of two fine-tuned BERT models. For other languages we propose a cross-lingual augmentation approach in order to enrich training data and we use Multilingual BERT to obtain sentence representations."
}