Entropy-Driven Dialog for Topic Classification: Detecting and Tackling Uncertainty

Tipo

Inproceedings

Fecha

2017-01-01

Autores

Manex Serras Saenz, Naiara Perez Miguel, María Inés Torres, María Arantzazu del Pozo Echezarreta

Libro

Dialogues with Social Robots

@Inproceedings{
author ={Manex Serras Saenz, Naiara Perez Miguel, María Inés Torres, María Arantzazu del Pozo Echezarreta},
title ={Entropy-Driven Dialog for Topic Classification: Detecting and Tackling Uncertainty},
booktitle ={Dialogues with Social Robots},
publisher ={Springer, Singapore},
editor ={Kristiina JokinenGraham Wilcock},
address ={Riekonlinna, Saariselkä, Finland},
date ={2017-01-01},
year ={2017},
pages ={171-182},
volume ={427},
series ={LNEE},
keys ={

Dialog System, System Turn Generation, Uncertainty Detection, Information Recovery

},
abstract ={

A frequent difficulty faced by developers of Dialogue Systems is the absence of a corpus of conversations to model the dialog statistically. Even when such a corpus is available, neither an agenda- nor a statistically-based dialog control logic are options if the domain knowledge is broad. This paper presents a module that automatically generates system-turn utterances to guide the user through the dialog. These system-turns are not established beforehand, and vary with each dialog. The module is valid for agenda-based and statistical approaches, being applicable in both types of corpora. Particularly, the task defined in this paper is the automation of a call-routing service. The proposed module is used when the user has not given enough information to route the call with high confidence. Doing so, and using the generated system-turns, the obtained information is improved through the dialog. The paper focuses on the development and operation of this module.

},
ISBN ={978-981-10-2584-6},
ISI ={Yes}
}