Speeding Up the Design of Dialogue Applications by Using Database Contents and Structure Information

Luis Fernando D'Haro, Ricardo de Cordoba, Juan Manuel Lucas, Roberto Barra and Ruben San-Segundo

SIGDIAL Workshop on Discourse and Dialogue (SIGDIAL 2009)
Queen Mary University of London, September 11-12, 2009

Summary

Nowadays, most commercial and research call centers are created using sophisticated and fully-feature development platforms. Surprisingly, most of them lack of some kind of acceleration strategy based on an automatic analysis of the contents or struc-ture of the backend database. This paper describes our efforts to incorporate this kind of information. Our main proposed strategies are: the generation of automatic state proposals for defining the dialogue flow network, the automatic selection of slots to be requested using mixed-initiative, the semi-automatic generation of SQL statements, and the quick generation of the data model and connection with the data-base fields. Subjective and objective evaluations demonstrate the advantages of using the accelerations and the high accep-tance of the platform and its accelerations.