Interactive Evaluation Of Dialog On Dstc9
Metriken
Coherent
Consistent
Diversity
Error Recovery
Flexible
Informative
Inquisitive
Likeable
Overall Human Rating
Topic Depth
Understanding
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Coherent | Consistent | Diversity | Error Recovery | Flexible | Informative | Inquisitive | Likeable | Overall Human Rating | Topic Depth | Understanding |
|---|---|---|---|---|---|---|---|---|---|---|---|
| a-unified-pre-training-framework-for | 2.8017 | 0.9390 | 2.7441 | 2.7518 | 2.8000 | 2.7881 | 2.7949 | 2.7878 | 4.15 | 2.7678 | 2.8285 |