BRUMS at SemEval-2020 Task 12 : Transformer based Multilingual Offensive Language Identification in Social Media

In this paper, we describe the team \\textit{BRUMS} entry to OffensEval 2:\nMultilingual Offensive Language Identification in Social Media in SemEval-2020.\nThe OffensEval organizers provided participants with annotated datasets\ncontaining posts from social media in Arabic, Danish, English, Greek and\nTurkish. We present a multilingual deep learning model to identify offensive\nlanguage in social media. Overall, the approach achieves acceptable evaluation\nscores, while maintaining flexibility between languages.\n