@inproceedings{vodolan-etal-2017-hybrid,
title = "Hybrid Dialog State Tracker with {ASR} Features",
author = "Vodol{\'a}n, Miroslav and
Kadlec, Rudolf and
Kleindienst, Jan",
editor = "Lapata, Mirella and
Blunsom, Phil and
Koller, Alexander",
booktitle = "Proceedings of the 15th Conference of the {E}uropean Chapter of the Association for Computational Linguistics: Volume 2, Short Papers",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/E17-2033",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vodolan-etal-2017-hybrid">
<titleInfo>
<title>Hybrid Dialog State Tracker with ASR Features</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miroslav</namePart>
<namePart type="family">Vodolán</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rudolf</namePart>
<namePart type="family">Kadlec</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Kleindienst</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mirella</namePart>
<namePart type="family">Lapata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phil</namePart>
<namePart type="family">Blunsom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Koller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">vodolan-etal-2017-hybrid</identifier>
<location>
<url>https://aclanthology.org/E17-2033</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>205</start>
<end>210</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hybrid Dialog State Tracker with ASR Features
%A Vodolán, Miroslav
%A Kadlec, Rudolf
%A Kleindienst, Jan
%Y Lapata, Mirella
%Y Blunsom, Phil
%Y Koller, Alexander
%S Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F vodolan-etal-2017-hybrid
%X 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.
%U https://aclanthology.org/E17-2033
%P 205-210
Markdown (Informal)
[Hybrid Dialog State Tracker with ASR Features](https://aclanthology.org/E17-2033) (Vodolán et al., EACL 2017)
ACL
- Miroslav Vodolán, Rudolf Kadlec, and Jan Kleindienst. 2017. Hybrid Dialog State Tracker with ASR Features. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 205–210, Valencia, Spain. Association for Computational Linguistics.