COMER generates belief states hierarchically with a shared sequence decoder, achieving 48.79% joint goal accuracy on MultiWOZ and near-state-of-the-art on WoZ2.0, while claiming O(1) inference time relative to the predefined ontology.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generation
COMER generates belief states hierarchically with a shared sequence decoder, achieving 48.79% joint goal accuracy on MultiWOZ and near-state-of-the-art on WoZ2.0, while claiming O(1) inference time relative to the predefined ontology.