Incremental LSTM-based Dialog State Tracker

A dialog state tracker is an important component in modern spoken dialog systems. We present an incremental dialog state tracker, based on LSTM networks. It directly uses automatic speech recognition hypotheses to track the state. We also present the key non-standard aspects of the model that bring...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zilka, Lukas, Jurcicek, Filip
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Zilka, Lukas
Jurcicek, Filip
description A dialog state tracker is an important component in modern spoken dialog systems. We present an incremental dialog state tracker, based on LSTM networks. It directly uses automatic speech recognition hypotheses to track the state. We also present the key non-standard aspects of the model that bring its performance close to the state-of-the-art and experimentally analyze their contribution: including the ASR confidence scores, abstracting scarcely represented values, including transcriptions in the training data, and model averaging.
doi_str_mv 10.48550/arxiv.1507.03471
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1507_03471</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1507_03471</sourcerecordid><originalsourceid>FETCH-LOGICAL-a671-d6b2903cc3f0b1280c8fb6bf39f7c80a3b1c14c831941394225109fb282accb83</originalsourceid><addsrcrecordid>eNotzrFuwjAQgGEvHSroA3RqdpRw53MSe6woUKSgDmSPzoeNIgKtTFSVt68Knf7t16fUM0JhbFnCnNNP_11gCXUBZGp8VLPNWVI4hfPIQ9bs2m3u-RL22VvPw-ch2408hqxNLMeQpuoh8nAJT_-dqHa1bBfvefOx3ixem5yrGvN95bUDEqEIHrUFsdFXPpKLtVhg8ihoxBI6g-SM1iWCi15bzSLe0kS93Lc3bfeV-hOna_en7m5q-gUvXzrf</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Incremental LSTM-based Dialog State Tracker</title><source>arXiv.org</source><creator>Zilka, Lukas ; Jurcicek, Filip</creator><creatorcontrib>Zilka, Lukas ; Jurcicek, Filip</creatorcontrib><description>A dialog state tracker is an important component in modern spoken dialog systems. We present an incremental dialog state tracker, based on LSTM networks. It directly uses automatic speech recognition hypotheses to track the state. We also present the key non-standard aspects of the model that bring its performance close to the state-of-the-art and experimentally analyze their contribution: including the ASR confidence scores, abstracting scarcely represented values, including transcriptions in the training data, and model averaging.</description><identifier>DOI: 10.48550/arxiv.1507.03471</identifier><language>eng</language><subject>Computer Science - Computation and Language</subject><creationdate>2015-07</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1507.03471$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1507.03471$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Zilka, Lukas</creatorcontrib><creatorcontrib>Jurcicek, Filip</creatorcontrib><title>Incremental LSTM-based Dialog State Tracker</title><description>A dialog state tracker is an important component in modern spoken dialog systems. We present an incremental dialog state tracker, based on LSTM networks. It directly uses automatic speech recognition hypotheses to track the state. We also present the key non-standard aspects of the model that bring its performance close to the state-of-the-art and experimentally analyze their contribution: including the ASR confidence scores, abstracting scarcely represented values, including transcriptions in the training data, and model averaging.</description><subject>Computer Science - Computation and Language</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2015</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzrFuwjAQgGEvHSroA3RqdpRw53MSe6woUKSgDmSPzoeNIgKtTFSVt68Knf7t16fUM0JhbFnCnNNP_11gCXUBZGp8VLPNWVI4hfPIQ9bs2m3u-RL22VvPw-ch2408hqxNLMeQpuoh8nAJT_-dqHa1bBfvefOx3ixem5yrGvN95bUDEqEIHrUFsdFXPpKLtVhg8ihoxBI6g-SM1iWCi15bzSLe0kS93Lc3bfeV-hOna_en7m5q-gUvXzrf</recordid><startdate>20150713</startdate><enddate>20150713</enddate><creator>Zilka, Lukas</creator><creator>Jurcicek, Filip</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20150713</creationdate><title>Incremental LSTM-based Dialog State Tracker</title><author>Zilka, Lukas ; Jurcicek, Filip</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a671-d6b2903cc3f0b1280c8fb6bf39f7c80a3b1c14c831941394225109fb282accb83</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2015</creationdate><topic>Computer Science - Computation and Language</topic><toplevel>online_resources</toplevel><creatorcontrib>Zilka, Lukas</creatorcontrib><creatorcontrib>Jurcicek, Filip</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Zilka, Lukas</au><au>Jurcicek, Filip</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Incremental LSTM-based Dialog State Tracker</atitle><date>2015-07-13</date><risdate>2015</risdate><abstract>A dialog state tracker is an important component in modern spoken dialog systems. We present an incremental dialog state tracker, based on LSTM networks. It directly uses automatic speech recognition hypotheses to track the state. We also present the key non-standard aspects of the model that bring its performance close to the state-of-the-art and experimentally analyze their contribution: including the ASR confidence scores, abstracting scarcely represented values, including transcriptions in the training data, and model averaging.</abstract><doi>10.48550/arxiv.1507.03471</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.1507.03471
ispartof
issn
language eng
recordid cdi_arxiv_primary_1507_03471
source arXiv.org
subjects Computer Science - Computation and Language
title Incremental LSTM-based Dialog State Tracker
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T15%3A50%3A39IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Incremental%20LSTM-based%20Dialog%20State%20Tracker&rft.au=Zilka,%20Lukas&rft.date=2015-07-13&rft_id=info:doi/10.48550/arxiv.1507.03471&rft_dat=%3Carxiv_GOX%3E1507_03471%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true