Generative Question Answering On Coqa
Metriken
F1-Score
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | 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 |