Hypers@DravidianLangTech-EACL2021: Offensive language identification in Dravidian code-mixed YouTube Comments and Posts

摘要

According to the use of Code-Mixed Offensive contents in social media posts, this study has the focus on such contents in low-resourced Dravidian languages such as Tamil, Kannada, and Malayalam using the bidirectional approach and fine-tuning strategies. Our proposed model got a 0.96 F1-score for Malayalam, 0.73 F1-score for Tamil, and 0.70 F1-score for Kannada based on the benchmark leader-board. Moreover, in the view of multilingual models, our modal ranked 3rd and achieved favorable results and confirmed the model as the best among all systems submitted to these shared tasks in these three languages.