Goal-conditioned User Modeling for Dialogue Systems using Stochastic Bi-Automata

Manex Serras, María Inés Torres, Arantza del Pozo

2019

Abstract

User Models (UM) are commonly employed to train and evaluate dialogue systems as they generate dialogue samples that simulate end-user behavior. This paper presents a stochastic approach for user modeling based in Attributed Probabilistic Finite State Bi-Automata (A-PFSBA). This framework allows the user model to be conditioned by the dialogue goal in task-oriented dialogue scenarios. In addition, the work proposes two novel smoothing policies that employ the K-nearest A-PFSBA states to infer the next UM action in unseen interactions. Experiments on the Dialogue State Tracking Challenge 2 (DSTC2) corpus provide results similar to the ones obtained through deep learning based user modeling approaches in terms of F1 measure. However the proposed Bi-Automata User Model (BAUM) requires less resources both of memory and computing time.

Download


Paper Citation


in Harvard Style

Serras M., Torres M. and del Pozo A. (2019). Goal-conditioned User Modeling for Dialogue Systems using Stochastic Bi-Automata.In Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-351-3, pages 128-134. DOI: 10.5220/0007359401280134


in Bibtex Style

@conference{icpram19,
author={Manex Serras and María Inés Torres and Arantza del Pozo},
title={Goal-conditioned User Modeling for Dialogue Systems using Stochastic Bi-Automata},
booktitle={Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2019},
pages={128-134},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007359401280134},
isbn={978-989-758-351-3},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Goal-conditioned User Modeling for Dialogue Systems using Stochastic Bi-Automata
SN - 978-989-758-351-3
AU - Serras M.
AU - Torres M.
AU - del Pozo A.
PY - 2019
SP - 128
EP - 134
DO - 10.5220/0007359401280134