NLU Intent Classification and Slot Filling on Braun corpora overall (test)
94.5PrecisionLuis
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| LuisBenchmark Run=August 20172018.05 | 94.5 | 88.9 | 91.6 | |
| SnipsBenchmark Run=January 20182018.05 | 89.6 | 85.8 | 87.7 | |
| API.aiBenchmark Run=August 20172018.05 | 87.1 | 56.7 | 68.7 | |
| RasaBenchmark Run=January 20182018.05 | 86.6 | 85.6 | 86.1 | |
| RasaBenchmark Run=August 20172018.05 | 78.9 | 85.5 | 82.1 | |
| IBM WatsonBenchmark Run=August 20172018.05 | 73.8 | 76.7 | 75.2 |