TFMN (PACL)

Reported on 4 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing4 results

Slot FillingonMixSNIPS
Micro F1· 2024-05-05
96.3
best: 97.2 (BiSLU)
A Two-Stage Prediction-Aware Contrastive Learning Framework for Multi-Intent NLU arXiv:2405.02925
Slot FillingonMixATIS
Micro F1· 2024-05-05
86.7
best: 90.5 (MISCA)
A Two-Stage Prediction-Aware Contrastive Learning Framework for Multi-Intent NLU arXiv:2405.02925
Intent DetectiononMixSNIPS
Accuracy· 2024-05-05
97.4
best: 98.4 (SSRAN)
A Two-Stage Prediction-Aware Contrastive Learning Framework for Multi-Intent NLU arXiv:2405.02925
Intent DetectiononMixATIS
Accuracy· 2024-05-05
82.9
best: 83.3 (DGIF)
A Two-Stage Prediction-Aware Contrastive Learning Framework for Multi-Intent NLU arXiv:2405.02925