A Practical Application of Evolving Fuzzy-Rule-Based Classifiers for the Development of Spoken Dialog Systems

Abstract : In this paper we present a statistical approach based on evolving Fuzzy-rule-based (FRB) classifiers for the development of dialog managers for spoken dialog systems. The dialog managers developed by means of our proposal select the next system action by considering a set of dynamic fuzzy rules that are automatically obtained by means of the application of the FRB classification process. Our approach has the main advantage of taking into account the data supplied by the user throughout the complete dialog history without causing scalability problems, also considering confidence measures provided by the recognition and understanding modules. The use of EFS also allows to process streaming data on-line in real time, thus dynamically evolving the structure and operation of the dialog model based on the interaction of the dialog system with its users. We also describe the application of our proposal to develop a dialog system providing railway information.
Document type :
Conference papers
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.inria.fr/hal-01391328
Contributor : Hal Ifip <>
Submitted on : Thursday, November 3, 2016 - 11:00:00 AM
Last modification on : Friday, December 1, 2017 - 1:16:36 AM
Long-term archiving on : Saturday, February 4, 2017 - 12:53:50 PM

File

978-3-662-44654-6_30_Chapter.p...
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

David Griol, José Iglesias, Agapito Ledezma, Araceli Sanchis. A Practical Application of Evolving Fuzzy-Rule-Based Classifiers for the Development of Spoken Dialog Systems. 10th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Sep 2014, Rhodes, Greece. pp.307-316, ⟨10.1007/978-3-662-44654-6_30⟩. ⟨hal-01391328⟩

Share

Metrics

Record views

63

Files downloads

97