Hate-speech-CNERG/dehatebert-mono-polish

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 0.723254 for a learning rate of 2e-5 . Please cite our paper in any published work that uses any of these resources . The model is used detecting hatespeech in Polish language . The training code can be found at this URL: rearXiv: 2004.06465. For more details about our paper: http://://://www.arxiv.com/aluru2020deep.org/sai Saketh Aluru,,