BERT-LARGE (Single+TriviaQA)

Reported on 3 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 Processing3 results

Question AnsweringonSQuAD1.1 dev
EM· 2018-10-11
84.2
best: 90.06 (T5-11B)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding arXiv:1810.04805
Question AnsweringonSQuAD1.1 dev
F1· 2018-10-11
91.1
best: 95.77 (XLNet+DSC)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding arXiv:1810.04805
Question AnsweringonSQuAD1.1
F1· 2018-10-11
91.8
best: 95.719 ({ANNA} (single model))
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding arXiv:1810.04805