SpanBERT (single model)

Reported on 4 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 Processing6 results

Question AnsweringonSQuAD1.1
EM· 2019-07-24
88.8
best: 90.622 ({ANNA} (single model))
SpanBERT: Improving Pre-training by Representing and Predicting Spans arXiv:1907.10529
Question AnsweringonSQuAD1.1
F1· 2019-07-24
94.6
best: 95.719 ({ANNA} (single model))
SpanBERT: Improving Pre-training by Representing and Predicting Spans arXiv:1907.10529
Question AnsweringonSQuAD1.1
EM
88.839
best: 90.622 ({ANNA} (single model))
Question AnsweringonSQuAD1.1
F1
94.635
best: 95.719 ({ANNA} (single model))
Question AnsweringonSQuAD2.0
EM
85.748
best: 90.939 (IE-Net (ensemble))
Question AnsweringonSQuAD2.0
F1
88.709
best: 93.214 (IE-Net (ensemble))