CODAH: An Adversarially Authored Question-Answer Dataset for Common Sense

8 Apr 2019Michael ChenMike D'ArcyAlisa LiuJared FernandezDoug Downey

Commonsense reasoning is a critical AI capability, but it is difficult to construct challenging datasets that test common sense. Recent neural question answering systems, based on large pre-trained models of language, have already achieved near-human-level performance on commonsense knowledge benchmarks... (read more)

PDF Abstract

Evaluation results from the paper


 SOTA for Question Answering on CODAH (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric name Metric value Global rank Uses extra
training data
Compare
Question Answering CODAH BERT Large Accuracy 69.6 # 1
Common Sense Reasoning CODAH BERT Large Accuracy 69.6 # 1