Implementation of a Statistical Dialogue Manager for Commercial Conversational Systems

  1. Pablo Cañas 1
  2. David Griol 2
  1. 1 École Polytechnique Féedérale de Lausanne (EPFL; Route Cantonale, 1015, Switzerland)
  2. 2 Universidad de Granada
    info

    Universidad de Granada

    Granada, España

    ROR https://ror.org/04njjy449

Livre:
15th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2020): Burgos, Spain ; September 2020
  1. Álvaro Herrero (coord.)
  2. Carlos Cambra (coord.)
  3. Daniel Urda (coord.)
  4. Javier Sedano (coord.)
  5. Héctor Quintián (coord.)
  6. Emilio Corchado (coord.)

Éditorial: Springer Suiza

ISBN: 978-3-030-57801-5 978-3-030-57802-2

Année de publication: 2021

Pages: 383-393

Congreso: International Conference on Soft Computing Models in Industrial and Environmental Applications SOCO (15. 2020. Burgos)

Type: Communication dans un congrès

Résumé

Conversational interfaces have recently become an ubiquitous element in both the personal sphere by improving individual’s quality of life, and industrial environments by the automation of services and its corresponding costs savings. However, designing the dialogue model used by these interfaces to decide the next response is a hard-toaccomplish task for complex conversational interactions. In this paper, we propose a statistical-based dialogue manager architecture, which provides flexibility to develop and maintain this module. Our proposal has been integrated with DialogFlow, a natural language understanding platform provided by Google to design conversational user interfaces. The proposed architecture has been assessed with a real use case for a train scheduling domain, proving that the user experience is of a high value and it can be integrated for commercial setups.