Paper Info
Title
Learning Bayesian networks for semantic frame composition in a spoken dialog system
Abstract
A stochastic approach based on Dynamic Bayesian Networks (DBNs) is introduced for spoken language understanding. DBN-based models allow to infer and then to compose semantic frame-based tree structures from speech transcriptions. Experimental results on the French Media dialog corpus show the appropriateness of the technique which both lead to good tree identification results and can provide the dialog system with n-best lists of scored hypotheses.
Year
Venue
Keywords
2009
north american chapter of the association for computational linguistics
learning bayesian network,n-best list,french media dialog corpus,semantic frame-based tree structure,good tree identification result,dialog system,speech transcription,language understanding,dbn-based model,semantic frame composition,dynamic bayesian networks,tree structure,bayesian network,dynamic bayesian network
Field
DocType
Citations 
Dialog box,Transcription (linguistics),Spoken dialog,Computer science,Speech recognition,Bayesian network,Natural language processing,Artificial intelligence,Tree structure,Dialog system,Spoken language,Dynamic Bayesian network
Conference
0
PageRank 
References 
Authors
0.34
5
3
Name
Order
Citations
PageRank
Marie-Jean Meurs19415.32
Fabrice Lefèvre218526.62
Renato De Mori3960161.75