HGN Model-reproduce

Reported on 6 benchmarks across 1 task

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
0.335
best: 0.727 (Beam Retrieval)
Question AnsweringonHotpotQA
ANS-F1
0.427
best: 0.85 (Beam Retrieval)
Question AnsweringonHotpotQA
JOINT-EM
0.11
best: 0.505 (Beam Retrieval)
Question AnsweringonHotpotQA
JOINT-F1
0.284
best: 0.775 (Beam Retrieval)
Question AnsweringonHotpotQA
SUP-EM
0.156
best: 0.663 (Beam Retrieval)
Question AnsweringonHotpotQA
SUP-F1
0.493
best: 0.901 (Beam Retrieval)