Dealing with out of domain questions in virtual characters

We consider the problem of designing virtual characters that support speech-based interactions in a limited domain. Previously we have shown that classification can be an effective and robust tool for selecting appropriate in-domain responses. In this paper, we consider the problem of dealing with o...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Patel, Ronakkumar, Leuski, Anton, Traum, David
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 131
container_issue
container_start_page 121
container_title
container_volume
creator Patel, Ronakkumar
Leuski, Anton
Traum, David
description We consider the problem of designing virtual characters that support speech-based interactions in a limited domain. Previously we have shown that classification can be an effective and robust tool for selecting appropriate in-domain responses. In this paper, we consider the problem of dealing with out-of-domain user questions. We introduce a taxonomy of out-of-domain response types. We consider three classification architectures for selecting the most appropriate out-of-domain responses. We evaluate these architectures and show that they significantly improve the quality of the response selection making the user’s interaction with the virtual character more natural and engaging.
doi_str_mv 10.1007/11821830_10
format Conference Proceeding
fullrecord <record><control><sourceid>pascalfrancis_acm_b</sourceid><recordid>TN_cdi_pascalfrancis_primary_19183241</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>19183241</sourcerecordid><originalsourceid>FETCH-LOGICAL-a283t-db08941dc73c141c7a3147cd5d4c85aa0afe3913f2d6355c617c304838cfbfc93</originalsourceid><addsrcrecordid>eNqN0D1PwzAQBmDzJVFKJ_5ABhhACvhyTuywofIpVWKB2bo4cWtIE7BTEP8eoyLBgsQtp9P76IaXsQPgp8C5PANQGSjkGvgG28NccJR5KfJNNoICIEUU5dZPgHKbjTjyLC2lwF02CeGJx0FQghcjdn7ZUOu6efLuhkXSr4akt0ndL8l1yeuqCYPru5DE4835YUVtYhbkyQyND_tsx1Ibmsn3HrPH66uH6W06u7-5m17MUsoUDmldcVUKqI1EAwKMJAQhTZ3XwqiciJNtsAS0WV1gnpsCpEEuFCpjK2tKHLOj9d8XCoZa66kzLugX75bkPzSUsY5MQHTHaxdi1M0br6u-fw6xKP3VnP7VXLQna0tm-TfTlXeNjfjwHxg_AcNocW4</addsrcrecordid><sourcetype>Index Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Dealing with out of domain questions in virtual characters</title><source>Springer Books</source><creator>Patel, Ronakkumar ; Leuski, Anton ; Traum, David</creator><contributor>Gratch, Jonathan ; Aylett, Ruth ; Ballin, Daniel ; Olivier, Patrick ; Young, Michael ; Young, Michael ; Aylett, Ruth ; Olivier, Patrick ; Ballin, Daniel ; Gratch, Jonathan</contributor><creatorcontrib>Patel, Ronakkumar ; Leuski, Anton ; Traum, David ; Gratch, Jonathan ; Aylett, Ruth ; Ballin, Daniel ; Olivier, Patrick ; Young, Michael ; Young, Michael ; Aylett, Ruth ; Olivier, Patrick ; Ballin, Daniel ; Gratch, Jonathan</creatorcontrib><description>We consider the problem of designing virtual characters that support speech-based interactions in a limited domain. Previously we have shown that classification can be an effective and robust tool for selecting appropriate in-domain responses. In this paper, we consider the problem of dealing with out-of-domain user questions. We introduce a taxonomy of out-of-domain response types. We consider three classification architectures for selecting the most appropriate out-of-domain responses. We evaluate these architectures and show that they significantly improve the quality of the response selection making the user’s interaction with the virtual character more natural and engaging.</description><identifier>ISSN: 0302-9743</identifier><identifier>ISBN: 3540375937</identifier><identifier>ISBN: 9783540375937</identifier><identifier>EISSN: 1611-3349</identifier><identifier>EISBN: 3540375945</identifier><identifier>EISBN: 9783540375944</identifier><identifier>DOI: 10.1007/11821830_10</identifier><language>eng</language><publisher>Berlin, Heidelberg: Springer-Verlag</publisher><subject>Applied sciences ; Computer science; control theory; systems ; Computer systems and distributed systems. User interface ; Exact sciences and technology ; Human Coder ; Intelligent User Interface ; Language Model ; Real Human ; Software ; Virtual Character</subject><ispartof>Intelligent Virtual Agents, 2006, p.121-131</ispartof><rights>Springer-Verlag Berlin Heidelberg 2006</rights><rights>2007 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/11821830_10$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/11821830_10$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>309,310,775,776,780,785,786,789,27902,38232,41418,42487</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&amp;idt=19183241$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><contributor>Gratch, Jonathan</contributor><contributor>Aylett, Ruth</contributor><contributor>Ballin, Daniel</contributor><contributor>Olivier, Patrick</contributor><contributor>Young, Michael</contributor><contributor>Young, Michael</contributor><contributor>Aylett, Ruth</contributor><contributor>Olivier, Patrick</contributor><contributor>Ballin, Daniel</contributor><contributor>Gratch, Jonathan</contributor><creatorcontrib>Patel, Ronakkumar</creatorcontrib><creatorcontrib>Leuski, Anton</creatorcontrib><creatorcontrib>Traum, David</creatorcontrib><title>Dealing with out of domain questions in virtual characters</title><title>Intelligent Virtual Agents</title><description>We consider the problem of designing virtual characters that support speech-based interactions in a limited domain. Previously we have shown that classification can be an effective and robust tool for selecting appropriate in-domain responses. In this paper, we consider the problem of dealing with out-of-domain user questions. We introduce a taxonomy of out-of-domain response types. We consider three classification architectures for selecting the most appropriate out-of-domain responses. We evaluate these architectures and show that they significantly improve the quality of the response selection making the user’s interaction with the virtual character more natural and engaging.</description><subject>Applied sciences</subject><subject>Computer science; control theory; systems</subject><subject>Computer systems and distributed systems. User interface</subject><subject>Exact sciences and technology</subject><subject>Human Coder</subject><subject>Intelligent User Interface</subject><subject>Language Model</subject><subject>Real Human</subject><subject>Software</subject><subject>Virtual Character</subject><issn>0302-9743</issn><issn>1611-3349</issn><isbn>3540375937</isbn><isbn>9783540375937</isbn><isbn>3540375945</isbn><isbn>9783540375944</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2006</creationdate><recordtype>conference_proceeding</recordtype><recordid>eNqN0D1PwzAQBmDzJVFKJ_5ABhhACvhyTuywofIpVWKB2bo4cWtIE7BTEP8eoyLBgsQtp9P76IaXsQPgp8C5PANQGSjkGvgG28NccJR5KfJNNoICIEUU5dZPgHKbjTjyLC2lwF02CeGJx0FQghcjdn7ZUOu6efLuhkXSr4akt0ndL8l1yeuqCYPru5DE4835YUVtYhbkyQyND_tsx1Ibmsn3HrPH66uH6W06u7-5m17MUsoUDmldcVUKqI1EAwKMJAQhTZ3XwqiciJNtsAS0WV1gnpsCpEEuFCpjK2tKHLOj9d8XCoZa66kzLugX75bkPzSUsY5MQHTHaxdi1M0br6u-fw6xKP3VnP7VXLQna0tm-TfTlXeNjfjwHxg_AcNocW4</recordid><startdate>20060101</startdate><enddate>20060101</enddate><creator>Patel, Ronakkumar</creator><creator>Leuski, Anton</creator><creator>Traum, David</creator><general>Springer-Verlag</general><general>Springer Berlin Heidelberg</general><general>Springer</general><scope>IQODW</scope></search><sort><creationdate>20060101</creationdate><title>Dealing with out of domain questions in virtual characters</title><author>Patel, Ronakkumar ; Leuski, Anton ; Traum, David</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a283t-db08941dc73c141c7a3147cd5d4c85aa0afe3913f2d6355c617c304838cfbfc93</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2006</creationdate><topic>Applied sciences</topic><topic>Computer science; control theory; systems</topic><topic>Computer systems and distributed systems. User interface</topic><topic>Exact sciences and technology</topic><topic>Human Coder</topic><topic>Intelligent User Interface</topic><topic>Language Model</topic><topic>Real Human</topic><topic>Software</topic><topic>Virtual Character</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Patel, Ronakkumar</creatorcontrib><creatorcontrib>Leuski, Anton</creatorcontrib><creatorcontrib>Traum, David</creatorcontrib><collection>Pascal-Francis</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Patel, Ronakkumar</au><au>Leuski, Anton</au><au>Traum, David</au><au>Gratch, Jonathan</au><au>Aylett, Ruth</au><au>Ballin, Daniel</au><au>Olivier, Patrick</au><au>Young, Michael</au><au>Young, Michael</au><au>Aylett, Ruth</au><au>Olivier, Patrick</au><au>Ballin, Daniel</au><au>Gratch, Jonathan</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Dealing with out of domain questions in virtual characters</atitle><btitle>Intelligent Virtual Agents</btitle><date>2006-01-01</date><risdate>2006</risdate><spage>121</spage><epage>131</epage><pages>121-131</pages><issn>0302-9743</issn><eissn>1611-3349</eissn><isbn>3540375937</isbn><isbn>9783540375937</isbn><eisbn>3540375945</eisbn><eisbn>9783540375944</eisbn><abstract>We consider the problem of designing virtual characters that support speech-based interactions in a limited domain. Previously we have shown that classification can be an effective and robust tool for selecting appropriate in-domain responses. In this paper, we consider the problem of dealing with out-of-domain user questions. We introduce a taxonomy of out-of-domain response types. We consider three classification architectures for selecting the most appropriate out-of-domain responses. We evaluate these architectures and show that they significantly improve the quality of the response selection making the user’s interaction with the virtual character more natural and engaging.</abstract><cop>Berlin, Heidelberg</cop><pub>Springer-Verlag</pub><doi>10.1007/11821830_10</doi><tpages>11</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0302-9743
ispartof Intelligent Virtual Agents, 2006, p.121-131
issn 0302-9743
1611-3349
language eng
recordid cdi_pascalfrancis_primary_19183241
source Springer Books
subjects Applied sciences
Computer science
control theory
systems
Computer systems and distributed systems. User interface
Exact sciences and technology
Human Coder
Intelligent User Interface
Language Model
Real Human
Software
Virtual Character
title Dealing with out of domain questions in virtual characters
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T17%3A21%3A23IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-pascalfrancis_acm_b&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Dealing%20with%20out%20of%20domain%20questions%20in%20virtual%20characters&rft.btitle=Intelligent%20Virtual%20Agents&rft.au=Patel,%20Ronakkumar&rft.date=2006-01-01&rft.spage=121&rft.epage=131&rft.pages=121-131&rft.issn=0302-9743&rft.eissn=1611-3349&rft.isbn=3540375937&rft.isbn_list=9783540375937&rft_id=info:doi/10.1007/11821830_10&rft_dat=%3Cpascalfrancis_acm_b%3E19183241%3C/pascalfrancis_acm_b%3E%3Curl%3E%3C/url%3E&rft.eisbn=3540375945&rft.eisbn_list=9783540375944&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true