Dialog state tracking (DST) suffers from severe data sparsity. While many natural language processing (NLP) tasks benefit from transfer learning and multi-task learning, in dialog these methods are limited by the amount of available data and by the specificity of dialog applications. In this work, we successfully utilize non-dialog data from unrelated NLP tasks to train dialog state trackers. This opens the door to the abundance of unrelated NLP corpora to mitigate the data sparsity issue inherent to DST.
@article{arxiv.2011.09379,
title = {Out-of-Task Training for Dialog State Tracking Models},
author = {Michael Heck and Carel van Niekerk and Nurul Lubis and Christian Geishauser and Hsien-Chin Lin and Marco Moresi and Milica Gašić},
journal= {arXiv preprint arXiv:2011.09379},
year = {2020}
}
Comments
8 pages, 2 figures, to be published in Proceedings of the 28th International Conference on Computational Linguistics, Code at https://gitlab.cs.uni-duesseldorf.de/general/dsml/trippy-public