Hate-speech-CNERG/bert-base-uncased-hatexplain

The model is used for classifying a text as Hatespeech, Offensive, or Normal . It is trained using data from Gab and Twitter and Human Rationales . The dataset and models are available here: https://://://github.com/punyajoy/HateXplain. The paper is accepted at AAAI 2021. It will be published in the journal ArXiv: 2012.10289. For more details about our paper: http://://www.arXiv.org/harvard/hatexplain-research-report-harsh-test/harshtest-test-report.html. For details about the paper: www.ar,