Bi-LSTM-CRF

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

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

Speech2 results

DialogueonSwitchboard corpus
Accuracy· 2017-09-13
79.2
best: 85 (HGRU + Beam Search + Guided attention)
SOTA
Dialogue Act Sequence Labeling using Hierarchical encoder with CRF arXiv:1709.04250
DialogueonICSI Meeting Recorder Dialog Act (MRDA) corpus
Accuracy· 2017-09-13
90.9
best: 92.4 (Pretrained Hierarchical Transformer)
SOTA
Dialogue Act Sequence Labeling using Hierarchical encoder with CRF arXiv:1709.04250