Incorporating Instructional Prompts into a Unified Generative Framework for Joint Multiple Intent Detection and Slot Filling
Open paper
Benchmark
Model
Rank
Results
intent-detection-on-mixatis
UGEN
#1
Accuracy: 83.0
intent-detection-on-mixsnips
UGEN
#6
Accuracy: 96.9
slot-filling-on-mixatis
UGEN
#4
Micro F1: 89.2
slot-filling-on-mixsnips
UGEN
#7
Micro F1: 95.0
Rank counts only results with a code link.