Offensive Content
otherentity
ID: offensivecontent
Related Papers
UBC-NLP at SemEval-2019 Task 6: Ensemble Learning of Offensive Content With Enhanced Training Data
AbstractWe examine learning offensive content on Twitter with limited, imbalanced data. For the purpose, we investigate the utility of using various data enhancement methods with a host of classical ensemble …...
Offensive Content Detection via Synthetic Code-Switched Text
AbstractThe prevalent use of offensive content in social media has become an important reason for concern for online platforms (customer service chat-boxes, social media platforms, etc). Classifying offensive and hate-speech …...
Red Teaming Language Models with Language Models
AbstractLanguage Models (LMs) often cannot be deployed because of their potential to harm users in hard-to-predict ways. Prior work identifies harmful behaviors before deployment by using human annotators to hand-write …...