MultiQA

Reported on 8 benchmarks across 1 task · 1 paper · 1 SOTA

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

Natural Language Processing8 results

Question AnsweringonMultiTQ
Hits@1· 2020-11-04
29.3
best: 79.7 (Prog-TQA)
SOTA
Muti-view Mouse Social Behaviour Recognition with Deep Graphical Model arXiv:2011.02451
Question AnsweringonMultiTQ
Hits@10· 2020-11-04
44.1
best: 91 (Prog-TQA)
Muti-view Mouse Social Behaviour Recognition with Deep Graphical Model arXiv:2011.02451
Question AnsweringonHotpotQA
ANS-EM
0.307
best: 0.727 (Beam Retrieval)
Question AnsweringonHotpotQA
ANS-F1
0.402
best: 0.85 (Beam Retrieval)
Question AnsweringonHotpotQA
JOINT-EM
0
best: 0.505 (Beam Retrieval)
Question AnsweringonHotpotQA
JOINT-F1
0
best: 0.775 (Beam Retrieval)
Question AnsweringonHotpotQA
SUP-EM
0
best: 0.663 (Beam Retrieval)
Question AnsweringonHotpotQA
SUP-F1
0
best: 0.901 (Beam Retrieval)