Fernández Martínez, Fernando and Ferreiros López, Javier and Córdoba Herralde, Ricardo de and Montero Martínez, Juan Manuel and San Segundo Hernández, Rubén and Pardo Muñoz, José Manuel (2009) A Bayesian Networks Approach for Dialog Modeling: The Fusion BN. In: IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP 2009, 19/04/2009 - 24/04/2009, Taipei, Taiwan.
Ver estadisticas de descargas para este eprint (solo desde ordenadores de la UPM)
| Item Type: | Presentation at Congress or Day (Article) | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Authors/Creators: |
| ||||||||||||||
| Title: | A Bayesian Networks Approach for Dialog Modeling: The Fusion BN | ||||||||||||||
| Event Title: | IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP 2009 | ||||||||||||||
| Event Dates: | 19/04/2009 - 24/04/2009 | ||||||||||||||
| Event Location: | Taipei, Taiwan | ||||||||||||||
| Title of Book: | Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP 2009 | ||||||||||||||
| Publisher: | IEEE | ||||||||||||||
| Date: | May 2009 | ||||||||||||||
| ISBN: | 978-1-4244-2353-8 | ||||||||||||||
| Department: | Electronic Engineering | ||||||||||||||
| Faculty: | E.T.S.I. Telecommunication (UPM) | ||||||||||||||
| Creative Commons licenses: | Recognition - No derivative works - No commercial | ||||||||||||||
| Item ID: | 5579 | ||||||||||||||
| Subjects: | Computer Science Electronics |
Texto completo disponible como:
![[img]](/style/images/fileicons/pdf.png)
| PDF 350Kb - Idioma: English |
Official URL: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4960702&tag=1
Abstract
Bayesian networks, BNs, are suitable for mixed-initiative dialog modeling allowing a more flexible and natural spoken interaction. This solution can be applied to identify the intention of the user considering the concepts extracted from the last utterance and the dialog context. Subsequently, in order to make a correct decision regarding how the dialog should continue, unnecessary, missing, wrong, optional and required concepts have to be detected according to the inferred goals. This information is useful to properly drive the dialog prompting for missing concepts, clarifying for wrong concepts, ignoring unnecessary concepts and retrieving those required and optional. This paper presents a novel BNs approach where a single BN is obtained from N goal-specific BNs through a fusion process. The new fusion BN enables a single concept analysis which is more consistent with the whole dialog context.
| Item Type: | Presentation at Congress or Day (Article) |
|---|---|
| Subjects: | Computer Science Electronics |
| Código ID: | 5579 |
| Depositado Por: | Memoria Investigacion |
| Depositado el: | 22 Dec 2010 11:16 |
| Last Modified: | 15 Feb 2011 12:04 |
Sólo para Personal del Archivo: editar este registro
