Question Answering On Codah

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

Paper TitleRepository
G-DAUG-Combo + RoBERTa-Large84.0Generative Data Augmentation for Commonsense Reasoning
BERT Large69.6CODAH: An Adversarially Authored Question-Answer Dataset for Common Sense
0 of 2 row(s) selected.
Question Answering On Codah | SOTA | HyperAI超神经