ProBERT

Reported on 4 benchmarks across 1 task

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing4 results

Coreference ResolutiononGAP
Bias (F/M)
0.97
best: 0.99 (Coref-MTL)
Coreference ResolutiononGAP
Feminine F1 (F)
91.1
best: 92.45 (Coref-MTL)
Coreference ResolutiononGAP
Masculine F1 (M)
94
Coreference ResolutiononGAP
Overall F1
92.5
best: 92.72 (Coref-MTL)