This paper presents a hybrid dialog state tracker that combines a rule based and a machine learning based approach to belief state tracking. Therefore, we call it a hybrid tracker. The machine learning in our tracker is realized by a Long Short Term Memory (LSTM) network. To our knowledge, our hybrid tracker sets a new state-of-the-art result for the Dialog State Tracking Challenge (DSTC) 2 dataset when the system uses only live SLU as its input.
Cite
@article{arxiv.1510.03710,
title = {Hybrid Dialog State Tracker},
author = {Miroslav Vodolán and Rudolf Kadlec and Jan Kleindienst},
journal= {arXiv preprint arXiv:1510.03710},
year = {2016}
}
Comments
Accepted to Machine Learning for SLU & Interaction NIPS 2015 Workshop. Model description in Section 2.1 simplified compared to the previous version