38 citations · 47 across the 8 of their papers we have counts for
3 papers · 1 filter
Rationale-Guided Few-Shot Classification to Detect Abusive Language
Punyajoy Saha, Divyanshu Sheth, Kushal Kedia +2
Abusive language is a concerning problem in online social media. Past research on detecting abusive language covers different platforms, languages, demographies, etc. However, mode…
CounterGeDi: A controllable approach to generate polite, detoxified and emotional counterspeech
Punyajoy Saha, Kanishk Singh, Adarsh Kumar +2
Recently, many studies have tried to create generation models to assist counter speakers by providing counterspeech suggestions for combating the explosive proliferation of online…
HateCheckHIn: Evaluating Hindi Hate Speech Detection Models
Mithun Das, Punyajoy Saha, Binny Mathew +1
Due to the sheer volume of online hate, the AI and NLP communities have started building models to detect such hateful content. Recently, multilingual hate is a major emerging chal…