UGEN

Reported on 4 benchmarks across 2 tasks

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
95
best: 97.2 (BiSLU)
Slot FillingonMixATIS
Micro F1
89.2
best: 90.5 (MISCA)
Intent DetectiononMixSNIPS
Accuracy
96.9
best: 98.4 (SSRAN)
Intent DetectiononMixATIS
Accuracy
83
best: 83.3 (DGIF)