Towards Universal Dialogue State Tracking

Liliang Ren, Kaige Xie, Lu Chen, Kai Yu


Abstract
Dialogue state tracker is the core part of a spoken dialogue system. It estimates the beliefs of possible user’s goals at every dialogue turn. However, for most current approaches, it’s difficult to scale to large dialogue domains. They have one or more of following limitations: (a) Some models don’t work in the situation where slot values in ontology changes dynamically; (b) The number of model parameters is proportional to the number of slots; (c) Some models extract features based on hand-crafted lexicons. To tackle these challenges, we propose StateNet, a universal dialogue state tracker. It is independent of the number of values, shares parameters across all slots, and uses pre-trained word vectors instead of explicit semantic dictionaries. Our experiments on two datasets show that our approach not only overcomes the limitations, but also significantly outperforms the performance of state-of-the-art approaches.
Anthology ID:
D18-1299
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2780–2786
Language:
URL:
https://www.aclweb.org/anthology/D18-1299
DOI:
10.18653/v1/D18-1299
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D18-1299.pdf
Video:
 https://vimeo.com/305944406