NASTIA : Negotiating Appointment Setting Interface

• Main Authors: El Asri, Layla, Lemonnier, Rémi, Laroche, Romain, Khouzaimi, Hatim, Pietquin, Olivier
• Other Authors: Georgia Tech Lorraine Metz, Ecole Nationale Supérieure des Arts et Metiers Metz-Georgia Institute of Technology Atlanta -Ecole Supérieure d'Electricité - SUPELEC (FRANCE)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université de Franche-Comté (UFC), Université Bourgogne Franche-Comté COMUE (UBFC)-Université Bourgogne Franche-Comté COMUE (UBFC), Orange Labs Issy les Moulineaux, France Télécom, Laboratoire Informatique d'Avignon (LIA), Avignon Université (AU)-Centre d'Enseignement et de Recherche en Informatique - CERI, Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)
• Format: Conference Object
• Language: English
• Published: HAL CCSD 2014
• Subjects: [INFO]Computer Science [cs]; [SPI]Engineering Sciences [physics]; Iceland
• Online Access: https://hal.inria.fr/hal-01107492

International audience This paper describes a French Spoken Dialogue System (SDS) named NASTIA (Negotiating Appointment SeTting InterfAce).Appointment scheduling is a hybrid task halfway between slot-filling and negotiation. NASTIA implements three different negotiationstrategies. These strategies were tested on 1734 dialogues with 385 users who interacted at most 5 times with the SDS and gave a ratingon a scale of 1 to 10 for each dialogue. Previous appointment scheduling systems were evaluated with the same experimental protocol.NASTIA is different from these systems in that it can adapt its strategy during the dialogue. The highest system task completion ratewith these systems was 81% whereas NASTIA had an 88% average and its best performing strategy even reached 92%. This strategyalso significantly outperformed previous systems in terms of overall user rating with an average of 8.28 against 7.40. The experimentalso enabled highlighting global recommendations for building spoken dialogue systems.