IRRR+

Reported on 6 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 Processing6 results

Question AnsweringonHotpotQA
ANS-EM· 2020-10-23
0.663
best: 0.727 (Beam Retrieval)
SOTA
Answering Open-Domain Questions of Varying Reasoning Steps from Text arXiv:2010.12527
Question AnsweringonHotpotQA
ANS-F1· 2020-10-23
0.791
best: 0.85 (Beam Retrieval)
SOTA
Answering Open-Domain Questions of Varying Reasoning Steps from Text arXiv:2010.12527
Question AnsweringonHotpotQA
JOINT-EM· 2020-10-23
0.428
best: 0.505 (Beam Retrieval)
SOTA
Answering Open-Domain Questions of Varying Reasoning Steps from Text arXiv:2010.12527
Question AnsweringonHotpotQA
JOINT-F1· 2020-10-23
0.696
best: 0.775 (Beam Retrieval)
Answering Open-Domain Questions of Varying Reasoning Steps from Text arXiv:2010.12527
Question AnsweringonHotpotQA
SUP-EM· 2020-10-23
0.569
best: 0.663 (Beam Retrieval)
Answering Open-Domain Questions of Varying Reasoning Steps from Text arXiv:2010.12527
Question AnsweringonHotpotQA
SUP-F1· 2020-10-23
0.832
best: 0.901 (Beam Retrieval)
Answering Open-Domain Questions of Varying Reasoning Steps from Text arXiv:2010.12527