Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering

Open paper

Benchmark	Model	Rank	Results
common-sense-reasoning-on-commonsenseqa	RoBERTa+HyKAS Ma et al. (2019)	–	Accuracy: 73.2
sentence-completion-on-hellaswag	HyKAS+CSKG	–	Accuracy: 85.0