Title
Learning to balance grounding rationales for dialogue systems
Abstract
This paper reports on an experiment that investigates clarification subdialogues in intentionally noisy speech recognition. The architecture learns weights for mixtures of grounding strategies from examples provided by a human wizard embedded in the system. Results indicate that the architecture learns to eliminate misunderstandings reliably despite high word error rate.
Year
Venue
Keywords
2011
SIGDIAL Conference
high word error rate,noisy speech recognition,dialogue system,paper report,clarification subdialogues,human wizard
Field
DocType
Citations 
Architecture,Computer science,Word error rate,Ground,Artificial intelligence,Natural language processing,Wizard,Machine learning
Conference
6
PageRank 
References 
Authors
0.49
13
3
Name
Order
Citations
PageRank
Joshua Gordon171.91
Rebecca J. Passonneau2978160.46
Susan L. Epstein325354.78