Stack-Propagation (+BERT)

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 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 FillingonSNIPS
F1· 2019-09-05
97
best: 98.3 (CTRAN)
SOTA
A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding arXiv:1909.02188
Intent DetectiononSNIPS
Accuracy· 2019-09-05
99
best: 99.42 (CTRAN)
SOTA
A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding arXiv:1909.02188
Slot FillingonATIS
F1· 2019-09-05
0.961
best: 0.9846 (CTRAN)
A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding arXiv:1909.02188
Intent DetectiononATIS
Accuracy· 2019-09-05
97.5
best: 98.99 (Bi-model with decoder)
A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding arXiv:1909.02188