Question Answering 벤치마크
Question Answering on CODAH
| Rank | Model | Accuracy | Extra Training Data | Paper | Code | Year |
|---|---|---|---|---|---|---|
| 1 | G-DAUG-Combo + RoBERTa-Large | 84.0 | Generative Data Augmentation for Commonsense Reasoning | yangyiben/G-DAUG-c-Generative-Data-Augmentation-for-Commonsense-Reasoning | 2020 | |
| 2 | BERT Large | 69.6 | ✓ | CODAH: An Adversarially Authored Question-Answer Dataset for Common Sense | Websail-NU/AQuA · iit-nlp-research/chatgpt-crawler | 2019 |