A graph-structured LSTM with same-speaker skip connections and max-based cell updates improves dialogue act classification on the STAC corpus to 87.69% accuracy and 75.78% macro-F1.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dialogue Act Classification in Group Chats with DAG-LSTMs
A graph-structured LSTM with same-speaker skip connections and max-based cell updates improves dialogue act classification on the STAC corpus to 87.69% accuracy and 75.78% macro-F1.