Hierarchical Graph Network for Multi-hop Question Answering
Open paper
Benchmark
Model
Rank
Results
question-answering-on-hotpotqa
HGN + SemanticRetrievalMRS IR
#9
JOINT-F1: 0.599
ANS-EM: 0.567
ANS-F1: 0.692
SUP-EM: 0.500
…
Rank counts only results with a code link.