Why Is It Hate Speech? Masked Rationale Prediction for Explainable Hate Speech Detection
Open paper
Benchmark
Model
Rank
Results
hate-speech-detection-on-hatexplain
BERT-MRP
#1
AUROC: 0.862
Macro F1: 0.699
Accuracy: 0.704
hate-speech-detection-on-hatexplain
BERT-RP
#2
AUROC: 0.853
Macro F1: 0.693
Accuracy: 0.707
Rank counts only results with a code link.