Multi-Paragraph Reasoning with Knowledge-enhanced Graph Neural Network
Open paper
Benchmark
Model
Rank
Results
question-answering-on-hotpotqa
KGNN
–
JOINT-F1: 0.247
ANS-EM: 0.277
ANS-F1: 0.372
SUP-EM: 0.127
…
Rank counts only results with a code link.