Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unitary.ai.
A Python package to compute HONEST, a score to measure hurtful sentence completions in language models. Published at NAACL 2021.
Multitask Aggression Detection (MAD)
Python Version of Andrew Welter's Hatebase Wrapper
No description available
