Commonsense for Generative Multi-Hop Question Answering Tasks

Open paper
Benchmark Model Rank Results
question-answering-on-narrativeqaMHPGM + NOIC#3Rouge-L: 44.16BLEU-1: 43.63BLEU-4: 21.07METEOR: 19.03
question-answering-on-wikihopMHPGM + NOIC#4Test: 57.9

Rank counts only results with a code link.