Co-guiding Net

Reported on 4 benchmarks across 2 tasks · 1 paper · 3 SOTA

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

Natural Language Processing4 results

Slot FillingonMixATIS
Micro F1· 2022-10-19
89.8
best: 90.5 (MISCA)
SOTA
Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphs arXiv:2210.10375
Intent DetectiononMixSNIPS
Accuracy· 2022-10-19
97.7
best: 98.4 (SSRAN)
SOTA
Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphs arXiv:2210.10375
Intent DetectiononMixATIS
Accuracy· 2022-10-19
79.1
best: 83.3 (DGIF)
SOTA
Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphs arXiv:2210.10375
Slot FillingonMixSNIPS
Micro F1· 2022-10-19
95.1
best: 97.2 (BiSLU)
Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphs arXiv:2210.10375