Speaker: Ashwin Geet D’Sa
Date: August 29, 2019 at 10:30 – C005
The spectacular expansion of the Internet led to the development of a new sector in the natural language processing field: automatic Hate Speech detection, as in many countries hate speech is prohibited. There is no clear and formal definition of hate speech, offensive speech, toxic speech and abusive speech. For this presentation, we put all these terms under “umbrella” of toxic speech. As per the current work, we perform binary comment classification aiming to predict whether one comment is toxic or not. Our current contributions are the studies of different state-of-the-art unsupervised word representations and different DNN classifiers. We apply the proposed methodology to the English Wikipedia Detox corpus with human-labeled comments.