A Dynamic Graph Interactive Framework with Label-Semantic Injection for Spoken Language Understanding
Open paper
Benchmark
Model
Rank
Results
intent-detection-on-mixatis
DGIF
–
Accuracy: 83.3
intent-detection-on-mixsnips
DGIF
–
Accuracy: 97.8
slot-filling-on-mixatis
DGIF
–
Micro F1: 88.5
slot-filling-on-mixsnips
DGIF
–
Micro F1: 95.9
Rank counts only results with a code link.