Building a multi-headed model that’s capable of detecting di erent types of toxicity like threats, obscenity, insults, and identity-based hate better than Perspective’s current models .
MohisnFurkh/Toxic-Comment-Classification-Challenge
Building a multi-headed model that’s capable of detecting di erent types of toxicity like threats, obscenity, insults, and identity-based hate better than Perspective’s current models .
Jupyter Notebook