BERT + BiLSTM

Reported on 4 benchmarks across 1 task · 1 paper · 3 SOTA

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

Speech4 results

Dialogueonirc-disentanglement
F· 2020-04-04
46.8
SOTA
Pre-Trained and Attention-Based Neural Networks for Building Noetic Task-Oriented Dialogue Systems arXiv:2004.01940
Dialogueonirc-disentanglement
R· 2020-04-04
49.6
SOTA
Pre-Trained and Attention-Based Neural Networks for Building Noetic Task-Oriented Dialogue Systems arXiv:2004.01940
Dialogueonirc-disentanglement
VI· 2020-04-04
93.3
SOTA
Pre-Trained and Attention-Based Neural Networks for Building Noetic Task-Oriented Dialogue Systems arXiv:2004.01940
Dialogueonirc-disentanglement
P· 2020-04-04
44.3
best: 67 (FF ensemble: Intersect)
Pre-Trained and Attention-Based Neural Networks for Building Noetic Task-Oriented Dialogue Systems arXiv:2004.01940