Online Learning of Attributed Bi-Automata for Dialogue Management in Spoken Dialogue Systems

Autores: Manex Serras Saenz Arantza del Pozo Echezarreta María Inés Torres

Fecha: 17.05.2017


PDF

Abstract

Online learning of dialogue managers is a desirable but often costly property to obtain. Probabilistic Finite State Bi-Automata (PFSBA) have shown to provide a flexible and adaptive framework to achieve this goal. In this paper, an Attributed PFSBA (A-PSFBA) is implemented and experimentally compared with previous non-attributed PFSBA proposals. Then, a simple yet effective online learning algorithm that adapts the probabilistic structure of the Bi-Automata on the run is presented and evaluated. To this end, the User Model is also represented by an A-PFSBA and the impact of different user behaviors is tested. The proposed approaches are evaluated on the Let’s Go corpus, showing significant improvements on the dialogue success rates reported in previous works.

 

BIB_text

@Article {
title = {Online Learning of Attributed Bi-Automata for Dialogue Management in Spoken Dialogue Systems},
pages = {22-31},
volume = {10255},
keywds = {

Spoken Dialogue Systems, Online learning, Attributed Bi-Automata, Dialogue management


}
abstract = {

Online learning of dialogue managers is a desirable but often costly property to obtain. Probabilistic Finite State Bi-Automata (PFSBA) have shown to provide a flexible and adaptive framework to achieve this goal. In this paper, an Attributed PFSBA (A-PSFBA) is implemented and experimentally compared with previous non-attributed PFSBA proposals. Then, a simple yet effective online learning algorithm that adapts the probabilistic structure of the Bi-Automata on the run is presented and evaluated. To this end, the User Model is also represented by an A-PFSBA and the impact of different user behaviors is tested. The proposed approaches are evaluated on the Let’s Go corpus, showing significant improvements on the dialogue success rates reported in previous works.

 


}
isbn = {978-3-319-58838-4},
isi = {1},
doi = {10.1007/978-3-319-58838-4_3},
date = {2017-05-17},
year = {2017},
}
Vicomtech

Parque Científico y Tecnológico de Gipuzkoa,
Paseo Mikeletegi 57,
20009 Donostia / San Sebastián (España)

+(34) 943 309 230

Zorrotzaurreko Erribera 2, Deusto,
48014 Bilbao (España)

close overlay

Las cookies de publicidad comportamental son necesarias para cargar el contenido

Aceptar cookies de publicidad comportamental