Guiding attention in Sequence-to-sequence models for Dialogue Act prediction
Open paper
Benchmark
Model
Rank
Results
dialogue-act-classification-on-switchboard
HGRU + Beam Search + Guided attention
#1
Accuracy: 85.0
dialogue-act-classification-on-icsi-mrda
HGRU + Beam Search + Guided attention
#2
Accuracy: 91.6
Rank counts only results with a code link.