FABIR

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 Processing4 results

Question AnsweringonSQuAD1.1 dev
EM· 2018-10-22
65.1
best: 90.06 (T5-11B)
A Fully Attention-Based Information Retriever arXiv:1810.09580
Question AnsweringonSQuAD1.1 dev
F1· 2018-10-22
75.6
best: 95.77 (XLNet+DSC)
A Fully Attention-Based Information Retriever arXiv:1810.09580
Question AnsweringonSQuAD1.1
EM· 2018-10-22
67.744
best: 90.622 ({ANNA} (single model))
A Fully Attention-Based Information Retriever arXiv:1810.09580
Question AnsweringonSQuAD1.1
F1· 2018-10-22
77.605
best: 95.719 ({ANNA} (single model))
A Fully Attention-Based Information Retriever arXiv:1810.09580