Generative Question Answering On Coqa
Metrics
F1-Score
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | F1-Score |
|---|---|
| ernie-gen-an-enhanced-multi-flow-pre-training | 84.5 |
| coqa-a-conversational-question-answering | 45.4 |
| unified-language-model-pre-training-for | 82.5 |