Hybrid Dialog State Tracker with ASR Features

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.

[1]  Antoine Raux,et al.  The Dialog State Tracking Challenge Series: A Review , 2016, Dialogue Discourse.

[2]  Yonghong Yan,et al.  Markovian Discriminative Modeling for Dialog State Tracking , 2014, SIGDIAL Conference.

[3]  Lu Chen,et al.  Constrained Markov Bayesian Polynomial for Efficient Dialogue State Tracking , 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[4]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[5]  Sungjin Lee,et al.  Task Lineages: Dialog State Tracking for Flexible Interaction , 2016, SIGDIAL Conference.

[6]  Matthew Henderson,et al.  Word-Based Dialog State Tracking with Recurrent Neural Networks , 2014, SIGDIAL Conference.

[7]  Lu Chen,et al.  The SJTU System for Dialog State Tracking Challenge 2 , 2014, SIGDIAL Conference.

[8]  Hervé Frezza-Buet,et al.  YARBUS : Yet Another Rule Based belief Update System , 2015, ArXiv.

[9]  Matthew Henderson,et al.  The Second Dialog State Tracking Challenge , 2014, SIGDIAL Conference.

[10]  Jason D. Williams,et al.  Web-style ranking and SLU combination for dialog state tracking , 2014, SIGDIAL Conference.

[11]  Kee-Eung Kim,et al.  Optimizing Generative Dialog State Tracker via Cascading Gradient Descent , 2014, SIGDIAL Conference.

[12]  Miroslav Vodolán,et al.  Hybrid Dialog State Tracker , 2015, ArXiv.

[13]  Tsung-Hsien Wen,et al.  Neural Belief Tracker: Data-Driven Dialogue State Tracking , 2016, ACL.

[14]  Ronnie W. Smith.  Comparative Error Analysis of Dialog State Tracking , 2014, SIGDIAL Conference.

[15]  Matthew D. Zeiler.  ADADELTA: An Adaptive Learning Rate Method , 2012, ArXiv.

[16]  Miroslav Vodolán,et al.  Knowledge-based Dialog State Tracking , 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).