Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction
Open paper
Benchmark
Model
Rank
Results
question-answering-on-hotpotqa
QFE
–
JOINT-F1: 0.231
ANS-EM: 0.287
ANS-F1: 0.381
SUP-EM: 0.142
…
Rank counts only results with a code link.