Hate-speech-CNERG/dehatebert-mono-indonesian

The mono in the name refers to the monolingual setting, where the model is trained using only Arabic language data . It is finetuned on multilingual bert model . The best validation score achieved is 0.844494 for a learning rate of 2e-5 . Training code can be found at this URL: http://://://www.aluru2020deep.com/sai Saketh Aluru, Sai Saket and Mathew, Binny and Saha, Punyajoy and Mukherjee, Animesh. "Deep Learning Models for Multilingual Hate Speech Detection". Accepted at ECML-PKDD 2020. Please cite our paper in any,