Dialogue State Tracking On Wizard Of Oz
Metriken
Joint
Request
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Joint | Request |
|---|---|---|
| a-simple-but-effective-bert-model-for-dialog | 90.5 | 97.6 |
| global-locally-self-attentive-dialogue-state | 88.1 | 97.1 |
| effective-sequence-to-sequence-dialogue-state | 91 | - |
| a-sequence-to-sequence-approach-to-dialogue | 91.2 | - |
| scalable-neural-dialogue-state-tracking | 88.7 | 96.9 |
| towards-universal-dialogue-state-tracking | 88.9 | - |
| toward-scalable-neural-dialogue-state | 88.5 | 97.4 |
| neural-belief-tracker-data-driven-dialogue | 84.4 | 96.5 |
| Modell 9 | 70.8 | 87.1 |
| amendable-generation-for-dialogue-state | 91.37 | - |