Memory State Tracker: A Memory Network based Dialogue State Tracker

Di Wang, Simon O’Keefe

Abstract

Dialogue State Tracking (DST) is a core component towards task oriented dialogue system. It fills manually-set slots at each turn of an utterance, which indicate the current topics or user requirement. In this work we propose a memory based state tracker that includes a memory encoder which encodes the dialogue history into a memory vector, and then connects to a pointer network which makes predictions. Our model reached a joint goal accuracy of 49.16% on MultiWOZ 2.0 data set (Budzianowski et al., 2018) and 47.27% on MultiWOZ 2.1 data set (Eric et al., 2019), outperforming the benchmark result.

Download


Paper Citation


in Harvard Style

Wang D. and O’Keefe S. (2021). Memory State Tracker: A Memory Network based Dialogue State Tracker.In Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI, ISBN 978-989-758-484-8, pages 533-538. DOI: 10.5220/0010385705330538


in Bibtex Style

@conference{nlpinai21,
author={Di Wang and Simon O’Keefe},
title={Memory State Tracker: A Memory Network based Dialogue State Tracker},
booktitle={Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI,},
year={2021},
pages={533-538},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010385705330538},
isbn={978-989-758-484-8},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI,
TI - Memory State Tracker: A Memory Network based Dialogue State Tracker
SN - 978-989-758-484-8
AU - Wang D.
AU - O’Keefe S.
PY - 2021
SP - 533
EP - 538
DO - 10.5220/0010385705330538