{"id":"https://openalex.org/W4399427937","doi":"https://doi.org/10.1162/tacl_a_00672","title":"Visually Grounded Speech Models Have a Mutual Exclusivity Bias","display_name":"Visually Grounded Speech Models Have a Mutual Exclusivity Bias","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4399427937","doi":"https://doi.org/10.1162/tacl_a_00672"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00672","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1162/tacl_a_00672","pdf_url":null,"source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://dx.doi.org/10.1162/tacl_a_00672","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020033363","display_name":"Leanne Nortje","orcid":null},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Leanne Nortje","raw_affiliation_strings":["Electrical and Electronic Engineering, Stellenbosch University, South Africa. nortjeleanne@gmail.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Electronic Engineering, Stellenbosch University, South Africa. nortjeleanne@gmail.com","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013389452","display_name":"Dan Onea\u0163\u0103","orcid":"https://orcid.org/0000-0003-4354-4393"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Dan Onea\u0163\u0103","raw_affiliation_strings":["SpeeD Lab, University Politehnica of Bucharest, Romania. dan.oneata@gmail.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeeD Lab, University Politehnica of Bucharest, Romania. dan.oneata@gmail.com","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078855278","display_name":"Yevgen Matusevych","orcid":"https://orcid.org/0000-0003-2910-4025"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yevgen Matusevych","raw_affiliation_strings":["CLCG, University of Groningen, The Netherlands. yevgen.matusevych@rug.nl"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CLCG, University of Groningen, The Netherlands. yevgen.matusevych@rug.nl","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040305929","display_name":"Herman Kamper","orcid":"https://orcid.org/0000-0003-2980-3475"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Herman Kamper","raw_affiliation_strings":["Electrical and Electronic Engineering, Stellenbosch University, South Africa. kamperh@sun.ac.za"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Electronic Engineering, Stellenbosch University, South Africa. kamperh@sun.ac.za","institution_ids":["https://openalex.org/I26092322"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06218952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"755","last_page":"770"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980000257492065,"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":0.9980000257492065,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9976000189781189,"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/T12031","display_name":"Speech and dialogue systems","score":0.9966999888420105,"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":0.797691822052002},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5042446851730347},{"id":"https://openalex.org/keywords/grounded-theory","display_name":"Grounded theory","score":0.44708991050720215},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39081501960754395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34603869915008545},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3257538676261902},{"id":"https://openalex.org/keywords/qualitative-research","display_name":"Qualitative research","score":0.11584576964378357},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.08650761842727661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.797691822052002},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5042446851730347},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.44708991050720215},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39081501960754395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34603869915008545},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3257538676261902},{"id":"https://openalex.org/C190248442","wikidata":"https://www.wikidata.org/wiki/Q839486","display_name":"Qualitative research","level":2,"score":0.11584576964378357},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.08650761842727661},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1162/tacl_a_00672","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1162/tacl_a_00672","pdf_url":null,"source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:pure.rug.nl:openaire_cris_publications/8d01a4c0-206e-423f-87aa-046697a998d7","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/8d01a4c0-206e-423f-87aa-046697a998d7","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nortje, L, Onea\u0163\u0103, D, Matusevych, Y & Kamper, H 2024, 'Visually Grounded Speech Models Have a Mutual Exclusivity Bias', Transactions of the Association for Computational Linguistics, vol. 12, pp. 755-770. https://doi.org/10.1162/tacl_a_00672","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:0219842f5438432da410ebaf036ea30a","is_oa":false,"landing_page_url":"https://doaj.org/article/0219842f5438432da410ebaf036ea30a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 12 (2024)","raw_type":"article"},{"id":"pmh:oai:pure.rug.nl:publications/8d01a4c0-206e-423f-87aa-046697a998d7","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/8d01a4c0-206e-423f-87aa-046697a998d7","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Nortje, L, Onea\u0163\u0103, D, Matusevych, Y & Kamper, H 2024, 'Visually Grounded Speech Models Have a Mutual Exclusivity Bias', Transactions of the Association for Computational Linguistics, vol. 12, pp. 755-770. https://doi.org/10.1162/tacl_a_00672","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:zenodo.org:13985417","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00672","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, 12, 755-770, (2024-06-04)","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00672","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1162/tacl_a_00672","pdf_url":null,"source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1525264136","https://openalex.org/W1720344338","https://openalex.org/W1861492603","https://openalex.org/W1951724000","https://openalex.org/W1966109131","https://openalex.org/W1966387021","https://openalex.org/W2004413798","https://openalex.org/W2013596317","https://openalex.org/W2030527368","https://openalex.org/W2038056950","https://openalex.org/W2071800152","https://openalex.org/W2077807855","https://openalex.org/W2108598243","https://openalex.org/W2115733720","https://openalex.org/W2126562945","https://openalex.org/W2126957485","https://openalex.org/W2133623440","https://openalex.org/W2145410271","https://openalex.org/W2152371962","https://openalex.org/W2153076891","https://openalex.org/W2166571083","https://openalex.org/W2586148577","https://openalex.org/W2618530766","https://openalex.org/W2802557066","https://openalex.org/W2842511635","https://openalex.org/W2889313720","https://openalex.org/W2950133079","https://openalex.org/W2962753610","https://openalex.org/W2962862718","https://openalex.org/W2963330681","https://openalex.org/W2963571336","https://openalex.org/W2963654155","https://openalex.org/W2963720603","https://openalex.org/W2963902314","https://openalex.org/W3009215973","https://openalex.org/W3095361818","https://openalex.org/W3099142230","https://openalex.org/W3102219307","https://openalex.org/W3157861865","https://openalex.org/W3200287550","https://openalex.org/W4205145744","https://openalex.org/W4205957729","https://openalex.org/W4224875474","https://openalex.org/W4285110637","https://openalex.org/W4287630250","https://openalex.org/W4297808394","https://openalex.org/W4319862278","https://openalex.org/W4319862477","https://openalex.org/W4372267276","https://openalex.org/W4385823277","https://openalex.org/W4394773771","https://openalex.org/W4395470973","https://openalex.org/W6631190155","https://openalex.org/W6729977899","https://openalex.org/W6765416902","https://openalex.org/W6770596778","https://openalex.org/W6774314701","https://openalex.org/W6784934235","https://openalex.org/W6790019176","https://openalex.org/W6791263356","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6809593508","https://openalex.org/W6853731373"],"related_works":["https://openalex.org/W1546533203","https://openalex.org/W2054080977","https://openalex.org/W1511554945","https://openalex.org/W2015439768","https://openalex.org/W4361008414","https://openalex.org/W3040823075","https://openalex.org/W2092147963","https://openalex.org/W2620765995","https://openalex.org/W1535784397","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Abstract":[0],"When":[1],"children":[2],"learn":[3,68],"new":[4],"words,":[5],"they":[6],"employ":[7],"constraints":[8],"such":[9],"as":[10,45],"the":[11,48,56,60,129,133,153,172,178,191],"mutual":[12],"exclusivity":[13],"(ME)":[14],"bias:":[15],"A":[16],"novel":[17,23,96,105,185],"word":[18,43],"is":[19],"mapped":[20],"to":[21,92,169,181],"a":[22,27,79,95,98,104,138],"object":[24,100],"rather":[25],"than":[26],"familiar":[28,82,99,183],"one.":[29],"This":[30],"bias":[31,58,88,131,140,180],"has":[32],"been":[33],"studied":[34],"computationally,":[35],"but":[36],"only":[37],"in":[38,59,141,190],"models":[39,66,142],"that":[40,67],"use":[41],"discrete":[42],"representations":[44],"input,":[46],"ignoring":[47],"high":[49],"variability":[50],"of":[51,62,155],"spoken":[52],"words.":[53],"We":[54],"investigate":[55],"ME":[57,87,130,179],"context":[61],"visually":[63],"grounded":[64],"speech":[65,74,122],"from":[69],"natural":[70],"images":[71],"and":[72,84,97,111,123,184],"continuous":[73],"audio.":[75],"Concretely,":[76],"we":[77,114,176],"train":[78],"model":[80],"on":[81,166],"words":[83],"test":[85],"its":[86],"by":[89],"asking":[90],"it":[91],"select":[93],"between":[94],"when":[101,159],"queried":[102],"with":[103,116,137,143],"word.":[106],"To":[107],"simulate":[108],"prior":[109,145],"acoustic":[110],"visual":[112],"knowledge,":[113],"experiment":[115],"several":[117],"initialization":[118,135],"strategies":[119],"using":[120],"pretrained":[121],"vision":[124],"networks.":[125],"Our":[126],"findings":[127],"reveal":[128],"across":[132],"different":[134,160],"approaches,":[136],"stronger":[139],"more":[144],"(in":[146],"particular,":[147],"visual)":[148],"knowledge.":[149],"Additional":[150],"tests":[151],"confirm":[152],"robustness":[154],"our":[156],"results,":[157],"even":[158],"loss":[161],"functions":[162],"are":[163,187],"considered.":[164],"Based":[165],"detailed":[167],"analyses":[168],"piece":[170],"out":[171],"model\u2019s":[173],"representation":[174],"space,":[175],"attribute":[177],"how":[182],"classes":[186],"distinctly":[188],"separated":[189],"resulting":[192],"space.":[193]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}