NLU Intent Classification and Slot Filling on Ask Ubuntu Corpus (test)
88.5PrecisionLuis
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| LuisBenchmark Run=August 20172018.05 | 88.5 | 84.2 | 86.3 | |
| API.aiBenchmark Run=August 20172018.05 | 81.5 | 75.4 | 78.3 | |
| SnipsBenchmark Run=January 20182018.05 | 81.2 | 82.8 | 82 | |
| IBM WatsonBenchmark Run=August 20172018.05 | 80.7 | 82.5 | 81.6 | |
| RasaBenchmark Run=January 20182018.05 | 79.6 | 76.8 | 78.2 | |
| RasaBenchmark Run=August 20172018.05 | 79.1 | 82.3 | 80.7 |