RoBERTa (no data aug)

Reported on 2 benchmarks across 1 task · 1 paper

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

Natural Language Processing2 results

Question AnsweringonSQuAD2.0 dev
EM· uses extra data· 2019-07-26
86.5
best: 87.9 (XLNet (single model))
RoBERTa: A Robustly Optimized BERT Pretraining Approach arXiv:1907.11692
Question AnsweringonSQuAD2.0 dev
F1· uses extra data· 2019-07-26
89.4
best: 90.6 (XLNet (single model))
RoBERTa: A Robustly Optimized BERT Pretraining Approach arXiv:1907.11692