Question Answering On Molweni
Metriken
EM
F1
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | EM | F1 |
|---|---|---|
| self-and-pseudo-self-supervised-prediction-of | 49.2 | 64 |
| self-and-pseudo-self-supervised-prediction-of | 58 | 72.9 |
| enhanced-speaker-aware-multi-party-multi-turn | 58.6 | 72.2 |
| dadgraph-a-discourse-aware-dialogue-graph | 46.5 | 61.5 |