论文信息 - Learning Bayesian Networks for Semantic Frame Composition in a Spoken Dialog System

Learning Bayesian Networks for Semantic Frame Composition in a Spoken Dialog System

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.

Renato De Mori | Fabrice Lefèvre | Marie-Jean Meurs

[1] J. Lowe,et al. A Frame-Semantic Approach to Semantic Annotation , 1997 .

[2] Christopher R. Johnson,et al. Background to Framenet , 2003 .

[3] Steve J. Young,et al. Spoken language understanding using the Hidden Vector State Model , 2006, Speech Commun..

[4] Geoffrey Zweig,et al. The graphical models toolkit: An open source software system for speech and time-series processing , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5] F. Lefvre. Dynamic Bayesian Networks and Discriminative Classifiers for Multi-Stage Semantic Interpretation , 2007 .

[6] Fabrice Lefèvre. Dynamic Bayesian Networks and Discriminative Classifiers for Multi-Stage Semantic Interpretation , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[7] Andreas Stolcke,et al. SRILM - an extensible language modeling toolkit , 2002, INTERSPEECH.

[8] Jeff A. Bilmes,et al. Factored Language Models and Generalized Parallel Backoff , 2003, NAACL.

[9] Fabrice Lef. DYNAMIC BAYESIAN NETWORKS AND DISCRIMINATIVE CLASSIFIERS FOR MULTI-STAGE SEMANTIC INTERPRETATION , 2007 .