BERT-LARGE (Ensemble+TriviaQA)

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

Question AnsweringonSQuAD1.1 dev
EM· 2018-10-11
86.2
best: 90.06 (T5-11B)
SOTA
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding arXiv:1810.04805
Question AnsweringonSQuAD1.1 dev
F1· 2018-10-11
92.2
best: 95.77 (XLNet+DSC)
SOTA
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding arXiv:1810.04805
Question AnsweringonSQuAD1.1
F1· 2018-10-11
93.2
best: 95.719 ({ANNA} (single model))
SOTA
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding arXiv:1810.04805
Question AnsweringonSQuAD1.1
EM· 2018-10-11
87.4
best: 90.622 ({ANNA} (single model))
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding arXiv:1810.04805