BERT for Joint Intent Classification and Slot Filling

Open paper
Benchmark Model Rank Results
slot-filling-on-atisJoint BERT#3F1: 0.961
slot-filling-on-atisJoint BERT + CRF#6F1: 0.96
intent-detection-on-atisJoint BERT + CRF#4Accuracy: 97.9
intent-detection-on-atisJoint BERT#7Accuracy: 97.5

Rank counts only results with a code link.