Hate-speech-CNERG/dehatebert-mono-english

The mono in the name refers to the monolingual setting, where the model is trained using only English language data . It is finetuned on multilingual bert model . The best validation score achieved is 0.726030 for a learning rate of 2e-5 . Training code can be found here: https://://github.com/punyajoy/DE-LIMIT /DE-IMIT. For more details about our paper: http://://://www.sai.org/aluru2020deep/deep-learning-models-for-hate-speech-detection-training-model-test-ability. Please cite our paper in any,