Managing Multi-task Dialogs by Means of a Statistical Dialog Management Technique

Autor: Zoraida Callejas, José F. Quesada, David Griol
Rok vydání: 2021
Předmět:
Zdroj: Lecture Notes in Electrical Engineering ISBN: 9789811593222
IWSDS
Lecture Notes in Electrical Engineering
Lecture Notes in Electrical Engineering-Increasing Naturalness and Flexibility in Spoken Dialogue Interaction
Increasing Naturalness and Flexibility in Spoken Dialogue Interaction. Lecture Notes in Electrical Engineering
ISSN: 1876-1100
1876-1119
DOI: 10.1007/978-981-15-9323-9_6
Popis: One of the most demanding tasks when developing a dialog system consists of deciding the next system response considering the user’s actions and the dialog history, which is the fundamental responsibility related to dialog management. A statistical dialog management technique is proposed in this work to reduce the effort and time required to design the dialog manager. This technique allows not only an easy adaptation to new domains, but also to deal with the different subtasks for which the dialog system has been designed. The practical application of the proposed technique to develop a dialog system for a travel-planning domain shows that the use of task-specific dialog models increases the quality and number of successful interactions with the system in comparison with developing a single dialog model for the complete domain.
info:eu-repo/grantAgreement/EC/H2020/823907 CAVIAR project (MINECO, TEC2017-84593-C2-1-R, AEI/FEDER, UE)
Databáze: OpenAIRE