A Dynamic Graph Interactive Framework with Label-Semantic Injection for Spoken Language Understanding

Benchmark Model Rank Results
intent-detection-on-mixatisDGIFAccuracy: 83.3
intent-detection-on-mixsnipsDGIFAccuracy: 97.8
slot-filling-on-mixatisDGIFMicro F1: 88.5
slot-filling-on-mixsnipsDGIFMicro F1: 95.9