Comparison of Bayesian Discriminative and Generative Models for Dialogue State Tracking

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F13%3A10194692" target="_blank" >RIV/00216208:11320/13:10194692 - isvavai.cz</a>
Result on the web
<a href="http://www.sigdial.org/workshops/sigdial2013/proceedings/index.html" target="_blank" >http://www.sigdial.org/workshops/sigdial2013/proceedings/index.html</a>
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Comparison of Bayesian Discriminative and Generative Models for Dialogue State Tracking
Original language description
In this paper, we describe two dialogue state tracking models competing in the 2012 Dialogue State Tracking Challenge (DSTC). First, we detail a novel discriminative dialogue state tracker which directly estimates slot-level beliefs using deterministic state transition probability distribution. Second, we present a generative model employing a simple dependency structure to achieve fast inference. The models are evaluated on the DSTC data, and both significantly outperform the baseline DSTC tracker.
Czech name
—
Czech description
—

Project
<a href="/en/project/LK11221" target="_blank" >LK11221: Development of statistical methods for spoken dalogue systems</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2013
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
SIGDIAL '13: 14th Annual Meeting of the Special Interest Group on Discourse and Dialogue
ISBN
978-1-937284-95-4
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
452-457
Publisher name
The Association for Computational Linguistics
Place of publication
Stroudsburg, PA, USA
Event location
Metz, France
Event date
Aug 22, 2013
Type of event by nationality
CST - Celostátní akce
UT code for WoS article
—

Similar results(10)