T5 for Hate Speech, Augmented Data and Ensemble. (arXiv:2210.05480v1 [cs.CL])

We conduct relatively extensive investigations of automatic hate speech (HS)
detection using different state-of-the-art (SoTA) baselines over 11 subtasks of
6 different datasets. Our motivation is to determine which of the recent SoTA
models is best for automatic hate speech detection and what advantage methods
like data augmentation and ensemble may have on the best model, if any. We
carry out 6 cross-task investigations. We achieve new SoTA on two subtasks -
macro F1 scores of 91.73% and 53.21% for …

arxiv augmented data data ensemble hate speech speech