Generating sentence from motion by using large-scale and high-order N-grams

Generating sentence from motion by using large-scale and high-order N-grams

Motion recognition is an essential technology for social robots in various environments such as homes, offices and shopping center, where the robots are expected to understand human behavior and interact with them. In this paper, we present a system composed of three models: motion language model, n...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Goutsu, Yusuke, Takano, Wataru, Nakamura, Yoshihiko
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Computational modeling
Google
Hidden Markov models
Lattices
Natural languages
Probability
Training
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 156
container_issue
container_start_page 151
container_title
container_volume
creator Goutsu, Yusuke
Takano, Wataru
Nakamura, Yoshihiko
description Motion recognition is an essential technology for social robots in various environments such as homes, offices and shopping center, where the robots are expected to understand human behavior and interact with them. In this paper, we present a system composed of three models: motion language model, natural language model and integration inference model, and achieved to generate sentences from motions using large high-order N-grams. We confirmed not only that using higher-order N-grams improves precision in generating long sentences but also that the computational complexity of the proposed system is almost the same as our previous one. In addition, we improved the precision by aligning the graph structure representing generated sentences into confusion network form. This means that simplifying and compacting word sequences affect the precision of sentence generation.
doi_str_mv 10.1109/IROS.2013.6696346
format Conference Proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6696346</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6696346</ieee_id><sourcerecordid>6696346</sourcerecordid><originalsourceid>FETCH-LOGICAL-i241t-4f60d7fe36d06e6cfa761cb66e3b1bdeca804252bd0b51851fee6787248e0aae3</originalsourceid><addsrcrecordid>eNo9kM1KAzEURqMoWGsfQNzkBTLe_MxNupSitVgs-LMuyeTOdKQzI8m46NtLsbj6Dhw4i4-xWwmFlDC_X71t3gsFUheIc9QGz9i1NGg16tK5czZRstQCHOLFP5fuis1y_gIAadEqBxP2sqSekh_bvuGZ-pH6inidho53w9gOPQ8H_pOPdu9TQyJXfk_c95Hv2mYnhhQp8VfRJN_lG3ZZ-32m2Wmn7PPp8WPxLNab5WrxsBatMnIUpkaItiaNEZCwqr1FWQVE0kGGSJV3YFSpQoRQSlfKmgits8o4Au9JT9ndX7clou13ajufDtvTD_oX7-JP4g</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Generating sentence from motion by using large-scale and high-order N-grams</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Goutsu, Yusuke ; Takano, Wataru ; Nakamura, Yoshihiko</creator><creatorcontrib>Goutsu, Yusuke ; Takano, Wataru ; Nakamura, Yoshihiko</creatorcontrib><description>Motion recognition is an essential technology for social robots in various environments such as homes, offices and shopping center, where the robots are expected to understand human behavior and interact with them. In this paper, we present a system composed of three models: motion language model, natural language model and integration inference model, and achieved to generate sentences from motions using large high-order N-grams. We confirmed not only that using higher-order N-grams improves precision in generating long sentences but also that the computational complexity of the proposed system is almost the same as our previous one. In addition, we improved the precision by aligning the graph structure representing generated sentences into confusion network form. This means that simplifying and compacting word sequences affect the precision of sentence generation.</description><identifier>ISSN: 2153-0858</identifier><identifier>EISSN: 2153-0866</identifier><identifier>EISBN: 1467363588</identifier><identifier>EISBN: 9781467363587</identifier><identifier>DOI: 10.1109/IROS.2013.6696346</identifier><language>eng</language><publisher>IEEE</publisher><subject>Computational modeling ; Google ; Hidden Markov models ; Lattices ; Natural languages ; Probability ; Training</subject><ispartof>2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2013, p.151-156</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6696346$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6696346$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Goutsu, Yusuke</creatorcontrib><creatorcontrib>Takano, Wataru</creatorcontrib><creatorcontrib>Nakamura, Yoshihiko</creatorcontrib><title>Generating sentence from motion by using large-scale and high-order N-grams</title><title>2013 IEEE/RSJ International Conference on Intelligent Robots and Systems</title><addtitle>IROS</addtitle><description>Motion recognition is an essential technology for social robots in various environments such as homes, offices and shopping center, where the robots are expected to understand human behavior and interact with them. In this paper, we present a system composed of three models: motion language model, natural language model and integration inference model, and achieved to generate sentences from motions using large high-order N-grams. We confirmed not only that using higher-order N-grams improves precision in generating long sentences but also that the computational complexity of the proposed system is almost the same as our previous one. In addition, we improved the precision by aligning the graph structure representing generated sentences into confusion network form. This means that simplifying and compacting word sequences affect the precision of sentence generation.</description><subject>Computational modeling</subject><subject>Google</subject><subject>Hidden Markov models</subject><subject>Lattices</subject><subject>Natural languages</subject><subject>Probability</subject><subject>Training</subject><issn>2153-0858</issn><issn>2153-0866</issn><isbn>1467363588</isbn><isbn>9781467363587</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2013</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo9kM1KAzEURqMoWGsfQNzkBTLe_MxNupSitVgs-LMuyeTOdKQzI8m46NtLsbj6Dhw4i4-xWwmFlDC_X71t3gsFUheIc9QGz9i1NGg16tK5czZRstQCHOLFP5fuis1y_gIAadEqBxP2sqSekh_bvuGZ-pH6inidho53w9gOPQ8H_pOPdu9TQyJXfk_c95Hv2mYnhhQp8VfRJN_lG3ZZ-32m2Wmn7PPp8WPxLNab5WrxsBatMnIUpkaItiaNEZCwqr1FWQVE0kGGSJV3YFSpQoRQSlfKmgits8o4Au9JT9ndX7clou13ajufDtvTD_oX7-JP4g</recordid><startdate>20130101</startdate><enddate>20130101</enddate><creator>Goutsu, Yusuke</creator><creator>Takano, Wataru</creator><creator>Nakamura, Yoshihiko</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>20130101</creationdate><title>Generating sentence from motion by using large-scale and high-order N-grams</title><author>Goutsu, Yusuke ; Takano, Wataru ; Nakamura, Yoshihiko</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i241t-4f60d7fe36d06e6cfa761cb66e3b1bdeca804252bd0b51851fee6787248e0aae3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2013</creationdate><topic>Computational modeling</topic><topic>Google</topic><topic>Hidden Markov models</topic><topic>Lattices</topic><topic>Natural languages</topic><topic>Probability</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Goutsu, Yusuke</creatorcontrib><creatorcontrib>Takano, Wataru</creatorcontrib><creatorcontrib>Nakamura, Yoshihiko</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Goutsu, Yusuke</au><au>Takano, Wataru</au><au>Nakamura, Yoshihiko</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Generating sentence from motion by using large-scale and high-order N-grams</atitle><btitle>2013 IEEE/RSJ International Conference on Intelligent Robots and Systems</btitle><stitle>IROS</stitle><date>2013-01-01</date><risdate>2013</risdate><spage>151</spage><epage>156</epage><pages>151-156</pages><issn>2153-0858</issn><eissn>2153-0866</eissn><eisbn>1467363588</eisbn><eisbn>9781467363587</eisbn><abstract>Motion recognition is an essential technology for social robots in various environments such as homes, offices and shopping center, where the robots are expected to understand human behavior and interact with them. In this paper, we present a system composed of three models: motion language model, natural language model and integration inference model, and achieved to generate sentences from motions using large high-order N-grams. We confirmed not only that using higher-order N-grams improves precision in generating long sentences but also that the computational complexity of the proposed system is almost the same as our previous one. In addition, we improved the precision by aligning the graph structure representing generated sentences into confusion network form. This means that simplifying and compacting word sequences affect the precision of sentence generation.</abstract><pub>IEEE</pub><doi>10.1109/IROS.2013.6696346</doi><tpages>6</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 2153-0858
ispartof 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2013, p.151-156
issn 2153-0858
2153-0866
language eng
recordid cdi_ieee_primary_6696346
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Computational modeling
Google
Hidden Markov models
Lattices
Natural languages
Probability
Training
title Generating sentence from motion by using large-scale and high-order N-grams
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-08T05%3A04%3A51IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Generating%20sentence%20from%20motion%20by%20using%20large-scale%20and%20high-order%20N-grams&rft.btitle=2013%20IEEE/RSJ%20International%20Conference%20on%20Intelligent%20Robots%20and%20Systems&rft.au=Goutsu,%20Yusuke&rft.date=2013-01-01&rft.spage=151&rft.epage=156&rft.pages=151-156&rft.issn=2153-0858&rft.eissn=2153-0866&rft_id=info:doi/10.1109/IROS.2013.6696346&rft_dat=%3Cieee_6IE%3E6696346%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=1467363588&rft.eisbn_list=9781467363587&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6696346&rfr_iscdi=true