A copy-enhanced multi-encoder-decoder model for dialogue state tracking that generates unknown slot values by copying from both the dialogue and the ontology.
Neural computation pp
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
-
Copy-Enhanced Heterogeneous Information Learning for Dialogue State Tracking
A copy-enhanced multi-encoder-decoder model for dialogue state tracking that generates unknown slot values by copying from both the dialogue and the ontology.