Using Transfer-based Language Models to Detect Hateful and Offensive Language Online (Proceedings of the Fourth Workshop on Online Abuse and Harms)Using Transfer-based Language Models to Detect Hateful and Offensive Language Online (Proceedings of the Fourth Workshop on Online Abuse and Harms)

“The results indicate that the attention-based models profoundly confuse hate speech with offensive and normal language. However, the pre-trained models outperform state-of-the-art results in terms of accurately predicting the hateful