Abusive language detection on OffensEval 2019 (test)
0.829Macro F1Liu et al. (2019) (Best system)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Liu et al. (2019) (Best system)Mode=Original shared task best system2020.10 | 0.829 | 0.599 | |
| HateBERTMode=Fine-tuned, Evaluation=In-dataset, Aggregation=Average of 5 runs2020.10 | 0.809 | 0.723 | |
| BERTMode=Fine-tuned, Evaluation=In-dataset, Aggregation=Average of 5 runs2020.10 | 0.803 | 0.715 |