Improving Dialogue Smoothing with A-priori State Pruning

Manex Serras, María Inés Torres, Arantza Del Pozo

2020

Abstract

When Dialogue Systems (DS) face real usage, a challenge to solve is managing unforeseen situations without breaking the coherence of the dialogue. One way to achieve this is by redirecting the interaction to known dialogue states in a transparent way. This work proposes a simple a-priori pruning method to rule out invalid candidates when searching for similar dialogue states in unexpected scenarios. The proposed method is evaluated on a User Model (UM) based on Attributed Probabilistic Finite State Bi-Automata (A-PFSBA), trained on the Dialogue State Tracking Challenge 2 (DSTC2) corpus. Results show that the proposed technique improves response times and achieves higher F1 scores than previous A-PFSBA implementations and deep learning models.

Download


Paper Citation


in Harvard Style

Serras M., Torres M. and Pozo A. (2020). Improving Dialogue Smoothing with A-priori State Pruning. In Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-397-1, pages 607-614. DOI: 10.5220/0009184206070614


in Bibtex Style

@conference{icpram20,
author={Manex Serras and María Torres and Arantza Pozo},
title={Improving Dialogue Smoothing with A-priori State Pruning},
booktitle={Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2020},
pages={607-614},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009184206070614},
isbn={978-989-758-397-1},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Improving Dialogue Smoothing with A-priori State Pruning
SN - 978-989-758-397-1
AU - Serras M.
AU - Torres M.
AU - Pozo A.
PY - 2020
SP - 607
EP - 614
DO - 10.5220/0009184206070614