NLU Intent Classification and Slot Filling on web apps corpus (test)
82.8PrecisionLuis
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| LuisBenchmark Run=August 20172018.05 | 82.8 | 65.3 | 73 | |
| IBM WatsonBenchmark Run=August 20172018.05 | 82.8 | 58.5 | 68.6 | |
| API.aiBenchmark Run=August 20172018.05 | 81 | 38.2 | 51.9 | |
| SnipsBenchmark Run=January 20182018.05 | 65.5 | 65.5 | 65.5 | |
| RasaBenchmark Run=January 20182018.05 | 59.3 | 61.3 | 60.3 | |
| RasaBenchmark Run=August 20172018.05 | 46.6 | 72.4 | 56.7 |