Hybrid Dialog State Tracker with ASR Features
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F17%3A10372185" target="_blank" >RIV/00216208:11320/17:10372185 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Hybrid Dialog State Tracker with ASR Features
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2017
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers
ISBN
978-1-5108-3860-4
ISSN
—
e-ISSN
neuvedeno
Number of pages
6
Pages from-to
205-210
Publisher name
Association for Computational Linguistics
Place of publication
Stroudsburg, PA, USA
Event location
Valencia, Spain
Event date
Apr 3, 2017
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—