An attention-based reading comprehension model that points to slot values in the conversation, augmented by an explicit slot carryover model and a fixed-vocabulary hybrid, sets a new state-of-the-art on MultiWOZ-2.0 dialogue state tracking.
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
-
Dialog State Tracking: A Neural Reading Comprehension Approach
An attention-based reading comprehension model that points to slot values in the conversation, augmented by an explicit slot carryover model and a fixed-vocabulary hybrid, sets a new state-of-the-art on MultiWOZ-2.0 dialogue state tracking.