RoBERTa-Large

Reported on 4 benchmarks across 1 task · 1 paper · 3 SOTA

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

Natural Language Processing4 results

Reading ComprehensiononAdversarialQA
D(BERT): F1· uses extra data· 2020-02-02
65.5
SOTA
Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension arXiv:2002.00293
Reading ComprehensiononAdversarialQA
D(BiDAF): F1· uses extra data· 2020-02-02
74.1
SOTA
Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension arXiv:2002.00293
Reading ComprehensiononAdversarialQA
Overall: F1· uses extra data· 2020-02-02
64.4
SOTA
Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension arXiv:2002.00293
Reading ComprehensiononAdversarialQA
D(RoBERTa): F1· uses extra data· 2020-02-02
53.4
best: 54.4 (BERT-Large)
Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension arXiv:2002.00293