@InProceedings{vodolan-kadlec-kleindienst:2017:EACLshort,
  author    = {Vodol\'{a}n, Miroslav  and  Kadlec, Rudolf  and  Kleindienst, Jan},
  title     = {Hybrid Dialog State Tracker with ASR Features},
  booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {205--210},
  abstract  = {This paper presents a hybrid dialog state tracker enhanced by trainable Spoken
	Language Understanding (SLU) for slot-filling dialog systems. Our architecture
	is inspired by previously proposed neural-network-based belief-tracking
	systems. In addition, we extended some parts of our modular architecture with
	differentiable rules to allow end-to-end training. We hypothesize that these
	rules allow our tracker to generalize better than pure machine-learning based
	systems. For evaluation, we used the Dialog State Tracking Challenge (DSTC) 2
	dataset - a popular belief tracking testbed with dialogs from restaurant
	information system. To our knowledge, our hybrid tracker sets a new
	state-of-the-art result in three out of four categories within the DSTC2.},
  url       = {http://www.aclweb.org/anthology/E17-2033}
}