Hybrid Dialog State Tracker with ASR Features
Miroslav Vodolán, Rudolf Kadlec, Jan Kleindienst · 2017
This paper presents a hybrid dialog state tracker enhanced by trainable Spoken Language Understanding (SLU) for slotfilling dialog systems.Our architecture is inspired by previously proposed neuralnetwork-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 machinelearning 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 stateof-the-art result in three out of four categories within the DSTC2.