Speeding up the design of dialogue applications by using database contents and structure information

  • Authors:
  • L. F. D'Haro;R. Cordoba;J. M. Lucas;R. Barra-Chicote;R. San-Segundo

  • Affiliations:
  • Universidad Politécnica de Madrid, Spain;Universidad Politécnica de Madrid, Spain;Universidad Politécnica de Madrid, Spain;Universidad Politécnica de Madrid, Spain;Universidad Politécnica de Madrid, Spain

  • Venue:
  • SIGDIAL '09 Proceedings of the SIGDIAL 2009 Conference: The 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Nowadays, most commercial and research dialogue applications for 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 structure of the backend database. This paper describes our efforts to incorporate this kind of information which continues the work done in (D'Haro et al, 2006). 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 of the application and the connection with the database fields. Subjective and objective evaluations demonstrate the advantages of using the accelerations and their high acceptance, both in our current proposals and in previous work.