Answer Selection 벤치마크
Answer Selection on CICERO
| Rank | Model | Exact Match | Paper | Code | Year |
|---|---|---|---|---|---|
| 1 | T5-large | 77.68 | CICERO: A Dataset for Contextualized Commonsense Inference in Dialogues | declare-lab/CICERO | 2022 |
| 2 | Unified QA | 77.51 | CICERO: A Dataset for Contextualized Commonsense Inference in Dialogues | declare-lab/CICERO | 2022 |