{"id":"https://openalex.org/W3034240711","doi":"https://doi.org/10.24963/ijcai.2020/67","title":"EViLBERT: Learning Task-Agnostic Multimodal Sense Embeddings","display_name":"EViLBERT: Learning Task-Agnostic Multimodal Sense Embeddings","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3034240711","doi":"https://doi.org/10.24963/ijcai.2020/67","mag":"3034240711"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/67","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/67","pdf_url":"https://www.ijcai.org/proceedings/2020/0067.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0067.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077034449","display_name":"Agostina Calabrese","orcid":null},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Agostina Calabrese","raw_affiliation_strings":["Sapienza University of Rome","Sapienza NLP Group, Department of Computer Science, Sapienza University of Rome"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"Sapienza NLP Group, Department of Computer Science, Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079283776","display_name":"Michele Bevilacqua","orcid":"https://orcid.org/0000-0002-2717-1454"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Michele Bevilacqua","raw_affiliation_strings":["Sapienza University of Rome","Sapienza NLP Group, Department of Computer Science, Sapienza University of Rome"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"Sapienza NLP Group, Department of Computer Science, Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026648049","display_name":"Roberto Navigli","orcid":"https://orcid.org/0000-0003-3831-9706"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Roberto Navigli","raw_affiliation_strings":["Sapienza University of Rome","Sapienza NLP Group, Department of Computer Science, Sapienza University of Rome"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"Sapienza NLP Group, Department of Computer Science, Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077034449"],"corresponding_institution_ids":["https://openalex.org/I861853513"],"apc_list":null,"apc_paid":null,"fwci":0.3926,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.61342462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"481","last_page":"487"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9976000189781189,"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/T10028","display_name":"Topic Modeling","score":0.9932000041007996,"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":0.8417246341705322},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.723038911819458},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7015661001205444},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6444836258888245},{"id":"https://openalex.org/keywords/forcing","display_name":"Forcing (mathematics)","score":0.5744882822036743},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5448300242424011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5375729203224182},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5252102017402649},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4845699071884155},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4558507204055786},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.45553848147392273},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.4278906583786011},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3328794240951538},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0773668885231018}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8417246341705322},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.723038911819458},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7015661001205444},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6444836258888245},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.5744882822036743},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5448300242424011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5375729203224182},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5252102017402649},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4845699071884155},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4558507204055786},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.45553848147392273},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.4278906583786011},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3328794240951538},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0773668885231018},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C49204034","wikidata":"https://www.wikidata.org/wiki/Q52139","display_name":"Climatology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2020/67","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/67","pdf_url":"https://www.ijcai.org/proceedings/2020/0067.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma1.it:11573/1431898","is_oa":true,"landing_page_url":"http://hdl.handle.net/11573/1431898","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/67","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/67","pdf_url":"https://www.ijcai.org/proceedings/2020/0067.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4628848537","display_name":"Multilingual, Open-text Unified Syntax-independent SEmantics","funder_award_id":"726487","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5036817778","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innov","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8051717526","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8633428685","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innovat","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034240711.pdf","grobid_xml":"https://content.openalex.org/works/W3034240711.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1614298861","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W2081580037","https://openalex.org/W2108598243","https://openalex.org/W2120526973","https://openalex.org/W2120699290","https://openalex.org/W2123024445","https://openalex.org/W2131540451","https://openalex.org/W2219047839","https://openalex.org/W2250676463","https://openalex.org/W2250742840","https://openalex.org/W2277195237","https://openalex.org/W2436001372","https://openalex.org/W2560730294","https://openalex.org/W2568262903","https://openalex.org/W2740782137","https://openalex.org/W2745461083","https://openalex.org/W2798881773","https://openalex.org/W2896457183","https://openalex.org/W2950502294","https://openalex.org/W2950577311","https://openalex.org/W2963158451","https://openalex.org/W2963341956","https://openalex.org/W2966715458","https://openalex.org/W2968124245","https://openalex.org/W2970231061","https://openalex.org/W2970608575","https://openalex.org/W2970773744","https://openalex.org/W2997591391","https://openalex.org/W3016211260","https://openalex.org/W3034782826","https://openalex.org/W3035391111","https://openalex.org/W3121480429","https://openalex.org/W4386506836"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W2043093291","https://openalex.org/W2363545964"],"abstract_inverted_index":{"The":[0],"problem":[1],"of":[2,13,17,30,42,79,103,164],"grounding":[3],"language":[4],"in":[5,125],"vision":[6],"is":[7,35,69,87,117],"increasingly":[8],"attracting":[9],"scholarly":[10],"efforts.":[11],"As":[12],"now,":[14],"however,":[15],"most":[16],"the":[18,39,43,90,113,162],"approaches":[19],"have":[20],"been":[21],"limited":[22,40],"to":[23,38,50,71,110,142],"word":[24],"embeddings,":[25],"which":[26,68],"are":[27],"not":[28],"capable":[29],"handling":[31],"polysemous":[32],"words.":[33],"This":[34],"mainly":[36],"due":[37],"coverage":[41],"available":[44],"semantically-annotated":[45],"datasets,":[46],"hence":[47],"forcing":[48],"research":[49],"rely":[51],"on":[52,89],"alternative":[53],"technologies":[54],"(i.e.,":[55],"image":[56,73],"search":[57],"engines).":[58],"To":[59],"address":[60],"this":[61],"issue,":[62],"we":[63,154],"introduce":[64],"EViLBERT,":[65],"an":[66,76],"approach":[67,86],"able":[70],"perform":[72],"classification":[74],"over":[75,126,170],"open":[77],"set":[78],"concepts,":[80],"both":[81],"concrete":[82],"and":[83,97,179],"non-concrete.":[84],"Our":[85],"based":[88],"recently":[91],"introduced":[92],"Vision-Language":[93],"Pretraining":[94],"(VLP)":[95],"model,":[96],"builds":[98],"upon":[99],"a":[100,120,165,171],"manually-annotated":[101],"dataset":[102,178],"concept-image":[104],"pairs.":[105],"We":[106,133,175],"use":[107],"our":[108,136,149],"technique":[109],"clean":[111],"up":[112],"image-to-concept":[114],"mapping":[115],"that":[116,135,157],"provided":[118],"within":[119],"multilingual":[121],"knowledge":[122],"base,":[123],"resulting":[124],"258,000":[127],"images":[128],"associated":[129],"with":[130],"42,500":[131],"concepts.":[132],"show":[134,156],"VLP-based":[137],"model":[138],"can":[139],"be":[140],"used":[141],"create":[143],"multimodal":[144,159],"sense":[145],"embeddings":[146,160,180],"starting":[147],"from":[148],"automatically-created":[150],"dataset.":[151],"In":[152],"turn,":[153],"also":[155],"these":[158],"improve":[161],"performance":[163],"Word":[166],"Sense":[167],"Disambiguation":[168],"architecture":[169],"strong":[172],"unimodal":[173],"baseline.":[174],"release":[176],"code,":[177],"at":[181],"http://babelpic.org.":[182]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}