{"id":"https://openalex.org/W4294811326","doi":"https://doi.org/10.1109/tcds.2022.3204452","title":"Language-Model-Based Paired Variational Autoencoders for Robotic Language Learning","display_name":"Language-Model-Based Paired Variational Autoencoders for Robotic Language Learning","publication_year":2022,"publication_date":"2022-09-06","ids":{"openalex":"https://openalex.org/W4294811326","doi":"https://doi.org/10.1109/tcds.2022.3204452"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2022.3204452","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcds.2022.3204452","pdf_url":"https://ieeexplore.ieee.org/ielx7/7274989/7422051/09878160.pdf","source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/7274989/7422051/09878160.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070488643","display_name":"Ozan \u00d6zdemir","orcid":"https://orcid.org/0000-0003-2410-5192"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Ozan \u00d6zdemir","raw_affiliation_strings":["Department of Informatics, Knowledge Technology Group, University of Hamburg, Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0003-2410-5192","affiliations":[{"raw_affiliation_string":"Department of Informatics, Knowledge Technology Group, University of Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040045142","display_name":"Matthias Kerzel","orcid":"https://orcid.org/0000-0002-1378-0435"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Kerzel","raw_affiliation_strings":["Department of Informatics, Knowledge Technology Group, University of Hamburg, Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-1378-0435","affiliations":[{"raw_affiliation_string":"Department of Informatics, Knowledge Technology Group, University of Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102025003","display_name":"Cornelius Weber","orcid":"https://orcid.org/0000-0001-5163-938X"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cornelius Weber","raw_affiliation_strings":["Department of Informatics, Knowledge Technology Group, University of Hamburg, Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5163-938X","affiliations":[{"raw_affiliation_string":"Department of Informatics, Knowledge Technology Group, University of Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062333532","display_name":"Jae Hee Lee","orcid":"https://orcid.org/0000-0001-9840-780X"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jae Hee Lee","raw_affiliation_strings":["Department of Informatics, Knowledge Technology Group, University of Hamburg, Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Knowledge Technology Group, University of Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033486668","display_name":"Stefan Wermter","orcid":"https://orcid.org/0000-0003-1343-4775"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Wermter","raw_affiliation_strings":["Department of Informatics, Knowledge Technology Group, University of Hamburg, Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1343-4775","affiliations":[{"raw_affiliation_string":"Department of Informatics, Knowledge Technology Group, University of Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5070488643"],"corresponding_institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"],"apc_list":null,"apc_paid":null,"fwci":0.8163,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.73148453,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"15","issue":"4","first_page":"1812","last_page":"1824"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8544769287109375},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7666946053504944},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6709972620010376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6619288325309753},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6157922744750977},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5236663222312927},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5207988023757935},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5117887854576111},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4686816334724426},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44159257411956787},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4071333408355713}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8544769287109375},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7666946053504944},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6709972620010376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6619288325309753},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6157922744750977},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5236663222312927},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5207988023757935},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5117887854576111},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4686816334724426},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44159257411956787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4071333408355713},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcds.2022.3204452","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcds.2022.3204452","pdf_url":"https://ieeexplore.ieee.org/ielx7/7274989/7422051/09878160.pdf","source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2201.06317","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.06317","pdf_url":"https://arxiv.org/pdf/2201.06317","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1109/tcds.2022.3204452","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcds.2022.3204452","pdf_url":"https://ieeexplore.ieee.org/ielx7/7274989/7422051/09878160.pdf","source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G6276684567","display_name":null,"funder_award_id":"TRR 169","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4294811326.pdf","grobid_xml":"https://content.openalex.org/works/W4294811326.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2142344747","https://openalex.org/W2293634267","https://openalex.org/W2531409750","https://openalex.org/W2604838875","https://openalex.org/W2771461682","https://openalex.org/W2774441505","https://openalex.org/W2862846329","https://openalex.org/W2885804027","https://openalex.org/W2888471892","https://openalex.org/W2891503716","https://openalex.org/W2962716343","https://openalex.org/W2963086650","https://openalex.org/W2984287396","https://openalex.org/W2998012869","https://openalex.org/W3000086239","https://openalex.org/W3035695796","https://openalex.org/W3037680014","https://openalex.org/W3038033387","https://openalex.org/W3038245394","https://openalex.org/W3100307207","https://openalex.org/W3100675524","https://openalex.org/W3102561192","https://openalex.org/W3176484337","https://openalex.org/W3195535318","https://openalex.org/W3202006151","https://openalex.org/W3211640812","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6727690538","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6782889966","https://openalex.org/W6789006708"],"related_works":["https://openalex.org/W3049463507","https://openalex.org/W2936497627","https://openalex.org/W4288365749","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W4287598411","https://openalex.org/W3098382480","https://openalex.org/W3094871513","https://openalex.org/W3198458223","https://openalex.org/W4288267738"],"abstract_inverted_index":{"Human":[0],"infants":[1],"learn":[2,28],"language":[3,29,51,124,160,181,185],"while":[4,30],"interacting":[5,31],"with":[6,32,81,107,120,196],"their":[7,11,33,50],"environment":[8],"in":[9,53],"which":[10,116],"caregivers":[12],"may":[13],"describe":[14],"the":[15,70,73,89,98,118,134,141,145,151,162,171,184],"objects":[16,108],"and":[17,49,86],"actions":[18,48],"they":[19],"perform.":[20],"Similar":[21],"to":[22,136,157,190],"human":[23,199],"infants,":[24],"artificial":[25],"agents":[26],"can":[27,105],"environment.":[34],"In":[35],"this":[36],"work,":[37],"first,":[38],"we":[39,68,113],"present":[40],"a":[41,54,121,179],"neural":[42],"model":[43,119,135,163,182],"that":[44,97,144,177],"bidirectionally":[45],"binds":[46],"robot":[47],"descriptions":[52,143,155],"simple":[55],"object":[56],"manipulation":[57],"scenario.":[58],"Building":[59],"on":[60],"our":[61,188],"previous":[62],"Paired":[63],"Variational":[64],"Autoencoders":[65],"(PVAE)":[66],"model,":[67,125],"demonstrate":[69],"superiority":[71],"of":[72,83,91,109,153,166,170],"variational":[74],"autoencoder":[75],"over":[76],"standard":[77],"autoencoders":[78],"by":[79,87],"experimenting":[80],"cubes":[82],"different":[84,110],"colours,":[85],"enabling":[88,133],"production":[90],"alternative":[92],"vocabularies.":[93],"Additional":[94],"experiments":[95,175],"show":[96],"model\u2019s":[99],"channel-separated":[100],"visual":[101],"feature":[102],"extraction":[103],"module":[104],"cope":[106],"shapes.":[111],"Next,":[112],"introduce":[114],"PVAE-BERT,":[115],"equips":[117],"pretrained":[122,180],"large-scale":[123],"i.e.,":[126],"Bidirectional":[127],"Encoder":[128],"Representations":[129],"from":[130,198],"Transformers":[131],"(BERT),":[132],"go":[137],"beyond":[138],"comprehending":[139],"only":[140],"predefined":[142],"network":[146],"has":[147],"been":[148],"trained":[149],"on;":[150],"recognition":[152],"action":[154],"generalises":[156],"unconstrained":[158],"natural":[159],"as":[161,183],"becomes":[164],"capable":[165],"understanding":[167],"unlimited":[168],"variations":[169],"same":[172],"descriptions.":[173],"Our":[174],"suggest":[176],"using":[178],"encoder":[186],"allows":[187],"approach":[189],"scale":[191],"up":[192],"for":[193],"real-world":[194],"scenarios":[195],"instructions":[197],"users.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2022-09-06T00:00:00"}
