Rémi Calizzano, Malte Ostendorff, Georg Rehm. DFKI SLT at GermEval 2021: Multilingual Pre-training and Data Augmentation for the Classification of Toxicity in Social Media Comments. In Julian Risch, Anke Stoll, Lena Wilms, Michael Wiegand, editors, Proceedings of the GermEval 2021 Shared Task on the Identification of Toxic, Engaging, and Fact-Claiming Comments, GermEval@KONVENS 2021, Düsseldorf, Germany, September 6, 2021. pages 25-31, Association for Computational Linguistics, 2021. [doi]