direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Page Content

Contributed Book Chapters

go back to overview

A clustering approach to assess real user profiles in spoken dialogue systems
Citation key callejas2014a
Author Callejas, Zoraida and Griol, David and Engelbrecht, Klaus-Peter and Lopez-Cozar Delgado, Ramon
Title of Book Natural Interaction with Robots, Knowbots and Smartphones. Putting Spoken Dialog Systems into Practice
Pages 327–334
Year 2014
ISBN 978-1-4614-8279-6
DOI 10.1007/978-1-4614-8280-2_29
Location New York
Editor Mariani, Joseph and Rosset, Sophie and Garnier-Rizet, Martine and Devillers, Laurence
Publisher Springer
Abstract Evaluation methodologies for spoken dialogue systems try to provide an efficient means of assessing the quality of the system and/or predicting the user sat- isfaction. In order to so, they must be carried out over a corpus of dialogues which contains as many possible prospective or real user types as possible. In this paper we present a clustering approach to provide insight on whether user profiles can be au- tomatically detected from the interaction parameters and overall quality predictions, providing a way of corroborating the most representative features for defining user profiles. We have carried out different experiments over a corpus of 62 dialogues with the INSPIRE dialogue system, from which the clustering approach provided an efficient way of easily obtaining information about the suitability of distinguish- ing between different user groups to complete a more significative evaluation of the system.
Link to publication Download Bibtex entry

go back to overview

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Auxiliary Functions