Towards meaningful, grounded conversations with intelligent agents

As conversational agents become integral parts of many aspects of our lives, current approaches are reaching bottlenecks of performance that require increasing amounts of data or increasingly powerful models. It is also becoming clear that such agents are here to stay and accompany us for long perio...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Papangelis, Alexandros, Ultes, Stefan
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 Papangelis, Alexandros
Ultes, Stefan
description As conversational agents become integral parts of many aspects of our lives, current approaches are reaching bottlenecks of performance that require increasing amounts of data or increasingly powerful models. It is also becoming clear that such agents are here to stay and accompany us for long periods of time. If we are, therefore, to design agents that can deeply understand our world and evolve with it, we need to take a step back and revisit the trade-offs we have made in the current state of the art models. This paper argues that a) we need to shift from slot filling into a more realistic conversation paradigm; and b) that, to realize that paradigm, we need models that are able to handle concrete and abstract entities as well as evolving relations between them.
doi_str_mv 10.48550/arxiv.2006.15768
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2006_15768</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2006_15768</sourcerecordid><originalsourceid>FETCH-LOGICAL-a678-1e6889b0d420a6e3f812af0773f7ce1c3d7163acb2c122b6ed2268731d1becc93</originalsourceid><addsrcrecordid>eNotz71OwzAUhmEvDKjlApjwBTTBx25sd4SKP6lSl-zRiX0cLKUOstMW7h61sHzv9kkPY_cg6rVtGvGI-TueaimErqEx2t6y53Y6Y_aFHwhTTEM4jis-5OmYPHnupnSiXHCOUyr8HOdPHtNM4xgHSjPHy5Yluwk4Frr774K1ry_t9r3a7d8-tk-7CrWxFZC2dtMLv5YCNalgQWIQxqhgHIFT3oBW6HrpQMpek5dSW6PAQ0_ObdSCPfzdXhHdV44HzD_dBdNdMeoXZVhFrQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Towards meaningful, grounded conversations with intelligent agents</title><source>arXiv.org</source><creator>Papangelis, Alexandros ; Ultes, Stefan</creator><creatorcontrib>Papangelis, Alexandros ; Ultes, Stefan</creatorcontrib><description>As conversational agents become integral parts of many aspects of our lives, current approaches are reaching bottlenecks of performance that require increasing amounts of data or increasingly powerful models. It is also becoming clear that such agents are here to stay and accompany us for long periods of time. If we are, therefore, to design agents that can deeply understand our world and evolve with it, we need to take a step back and revisit the trade-offs we have made in the current state of the art models. This paper argues that a) we need to shift from slot filling into a more realistic conversation paradigm; and b) that, to realize that paradigm, we need models that are able to handle concrete and abstract entities as well as evolving relations between them.</description><identifier>DOI: 10.48550/arxiv.2006.15768</identifier><language>eng</language><subject>Computer Science - Human-Computer Interaction</subject><creationdate>2020-06</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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,777,882</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2006.15768$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2006.15768$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Papangelis, Alexandros</creatorcontrib><creatorcontrib>Ultes, Stefan</creatorcontrib><title>Towards meaningful, grounded conversations with intelligent agents</title><description>As conversational agents become integral parts of many aspects of our lives, current approaches are reaching bottlenecks of performance that require increasing amounts of data or increasingly powerful models. It is also becoming clear that such agents are here to stay and accompany us for long periods of time. If we are, therefore, to design agents that can deeply understand our world and evolve with it, we need to take a step back and revisit the trade-offs we have made in the current state of the art models. This paper argues that a) we need to shift from slot filling into a more realistic conversation paradigm; and b) that, to realize that paradigm, we need models that are able to handle concrete and abstract entities as well as evolving relations between them.</description><subject>Computer Science - Human-Computer Interaction</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz71OwzAUhmEvDKjlApjwBTTBx25sd4SKP6lSl-zRiX0cLKUOstMW7h61sHzv9kkPY_cg6rVtGvGI-TueaimErqEx2t6y53Y6Y_aFHwhTTEM4jis-5OmYPHnupnSiXHCOUyr8HOdPHtNM4xgHSjPHy5Yluwk4Frr774K1ry_t9r3a7d8-tk-7CrWxFZC2dtMLv5YCNalgQWIQxqhgHIFT3oBW6HrpQMpek5dSW6PAQ0_ObdSCPfzdXhHdV44HzD_dBdNdMeoXZVhFrQ</recordid><startdate>20200628</startdate><enddate>20200628</enddate><creator>Papangelis, Alexandros</creator><creator>Ultes, Stefan</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20200628</creationdate><title>Towards meaningful, grounded conversations with intelligent agents</title><author>Papangelis, Alexandros ; Ultes, Stefan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a678-1e6889b0d420a6e3f812af0773f7ce1c3d7163acb2c122b6ed2268731d1becc93</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Human-Computer Interaction</topic><toplevel>online_resources</toplevel><creatorcontrib>Papangelis, Alexandros</creatorcontrib><creatorcontrib>Ultes, Stefan</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Papangelis, Alexandros</au><au>Ultes, Stefan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Towards meaningful, grounded conversations with intelligent agents</atitle><date>2020-06-28</date><risdate>2020</risdate><abstract>As conversational agents become integral parts of many aspects of our lives, current approaches are reaching bottlenecks of performance that require increasing amounts of data or increasingly powerful models. It is also becoming clear that such agents are here to stay and accompany us for long periods of time. If we are, therefore, to design agents that can deeply understand our world and evolve with it, we need to take a step back and revisit the trade-offs we have made in the current state of the art models. This paper argues that a) we need to shift from slot filling into a more realistic conversation paradigm; and b) that, to realize that paradigm, we need models that are able to handle concrete and abstract entities as well as evolving relations between them.</abstract><doi>10.48550/arxiv.2006.15768</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2006.15768
ispartof
issn
language eng
recordid cdi_arxiv_primary_2006_15768
source arXiv.org
subjects Computer Science - Human-Computer Interaction
title Towards meaningful, grounded conversations with intelligent agents
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-17T17%3A14%3A35IST&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=Towards%20meaningful,%20grounded%20conversations%20with%20intelligent%20agents&rft.au=Papangelis,%20Alexandros&rft.date=2020-06-28&rft_id=info:doi/10.48550/arxiv.2006.15768&rft_dat=%3Carxiv_GOX%3E2006_15768%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