JointBERT-CAE

Reported on 6 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 Processing6 results

Slot FillingonATIS
F1
0.961
best: 0.9846 (CTRAN)
Slot FillingonSNIPS
F1
97
best: 98.3 (CTRAN)
Slot FillingonATIS (vi)
Slot F1
95.5
Intent DetectiononATIS
Accuracy
97.5
best: 98.99 (Bi-model with decoder)
Intent DetectiononSNIPS
Accuracy
98.3
best: 99.42 (CTRAN)
Intent DetectiononATIS (vi)
Intent Accuracy
97.7