Generative Question Answering On Coqa
평가 지표
F1-Score
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | F1-Score | Paper Title | Repository |
|---|---|---|---|
| ERNIE-GEN | 84.5 | ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation | |
| PGNet | 45.4 | CoQA: A Conversational Question Answering Challenge | |
| UniLM | 82.5 | Unified Language Model Pre-training for Natural Language Understanding and Generation |
0 of 3 row(s) selected.