{"id":"https://openalex.org/W3135099046","doi":"https://doi.org/10.1145/3404835.3463257","title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","display_name":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3135099046","doi":"https://doi.org/10.1145/3404835.3463257","mag":"3135099046"},"language":"en","primary_location":{"id":"doi:10.1145/3404835.3463257","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3404835.3463257","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3404835.3463257","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101757560","display_name":"Krishna Srinivasan","orcid":"https://orcid.org/0000-0003-1366-0895"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishna Srinivasan","raw_affiliation_strings":["Google, Mountain View, CA, USA","Google Mountain View CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Mountain View CA USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011489319","display_name":"Karthik Raman","orcid":"https://orcid.org/0000-0002-9311-7093"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karthik Raman","raw_affiliation_strings":["Google, Mountain View, CA, USA","Google Mountain View CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Mountain View CA USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015842400","display_name":"Jiecao Chen","orcid":"https://orcid.org/0009-0006-2512-4861"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiecao Chen","raw_affiliation_strings":["Google, Mountain View, CA, USA","Google Mountain View CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Mountain View CA USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032248436","display_name":"Michael Bendersky","orcid":"https://orcid.org/0000-0002-2941-6240"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Bendersky","raw_affiliation_strings":["Google, Mountain View, CA, USA","Google Mountain View CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Mountain View CA USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037200145","display_name":"Marc Najork","orcid":"https://orcid.org/0000-0003-1423-0854"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marc Najork","raw_affiliation_strings":["Google, Mountain View, CA, USA","Google Mountain View CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Mountain View CA USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2443","last_page":"2449"},"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/T10028","display_name":"Topic Modeling","score":0.9945999979972839,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9927999973297119,"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":0.8043733239173889},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6196002960205078},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5598729252815247},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5378562211990356},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.5140491724014282},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5115981698036194},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49245485663414},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.43604224920272827},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38552016019821167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8043733239173889},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6196002960205078},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5598729252815247},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5378562211990356},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.5140491724014282},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5115981698036194},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49245485663414},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43604224920272827},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38552016019821167},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3404835.3463257","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3404835.3463257","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2103.01913","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.01913","pdf_url":"https://arxiv.org/pdf/2103.01913","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3135099046","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2103.01913.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2103.01913","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.01913","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.57702/gjvr2zfc","is_oa":true,"landing_page_url":"https://doi.org/10.57702/gjvr2zfc","pdf_url":null,"source":{"id":"https://openalex.org/S7407053387","display_name":"TIB Data Manager","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.1145/3404835.3463257","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3404835.3463257","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1566289585","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1933349210","https://openalex.org/W1978924650","https://openalex.org/W2108598243","https://openalex.org/W2183341477","https://openalex.org/W2185175083","https://openalex.org/W2293344577","https://openalex.org/W2345720230","https://openalex.org/W2509282593","https://openalex.org/W2509490957","https://openalex.org/W2734663976","https://openalex.org/W2758129972","https://openalex.org/W2884476676","https://openalex.org/W2886641317","https://openalex.org/W2888070626","https://openalex.org/W2896457183","https://openalex.org/W2903343986","https://openalex.org/W2916754336","https://openalex.org/W2939455697","https://openalex.org/W2947018532","https://openalex.org/W2950761309","https://openalex.org/W2962843773","https://openalex.org/W2963115613","https://openalex.org/W2963331233","https://openalex.org/W2963527096","https://openalex.org/W2963909453","https://openalex.org/W2967593235","https://openalex.org/W2968124245","https://openalex.org/W2968880719","https://openalex.org/W2970608575","https://openalex.org/W2970854433","https://openalex.org/W2970869018","https://openalex.org/W2975501350","https://openalex.org/W2981852735","https://openalex.org/W2995460200","https://openalex.org/W2997591391","https://openalex.org/W2998356391","https://openalex.org/W3000226596","https://openalex.org/W3001555892","https://openalex.org/W3020257313","https://openalex.org/W3049302648","https://openalex.org/W3082274269","https://openalex.org/W3093517588","https://openalex.org/W3094502228","https://openalex.org/W3126337491","https://openalex.org/W3130033937","https://openalex.org/W3135367836","https://openalex.org/W4241298546","https://openalex.org/W6600134738"],"related_works":["https://openalex.org/W2886641317","https://openalex.org/W2963341956","https://openalex.org/W3135367836","https://openalex.org/W3126337491","https://openalex.org/W1861492603","https://openalex.org/W2970608575","https://openalex.org/W2277195237","https://openalex.org/W2194775991","https://openalex.org/W1889081078","https://openalex.org/W2970231061","https://openalex.org/W2963403868","https://openalex.org/W3182683290","https://openalex.org/W3104279398","https://openalex.org/W3034655362","https://openalex.org/W2745461083","https://openalex.org/W2613718673","https://openalex.org/W2185175083","https://openalex.org/W2109586012","https://openalex.org/W2101105183","https://openalex.org/W22168010"],"abstract_inverted_index":{"The":[0],"milestone":[1],"improvements":[2],"brought":[3],"about":[4],"by":[5,124,130],"deep":[6],"representation":[7],"learning":[8,36],"and":[9,22,41,114,159,175,212],"pre-training":[10],"techniques":[11,27],"have":[12],"led":[13],"to":[14,29,55,88,103,180],"large":[15,31],"performance":[16],"gains":[17],"across":[18,39,80],"downstream":[19,104],"NLP,":[20],"IR":[21],"Vision":[23],"tasks.":[24],"Multimodal":[25],"modeling":[26],"aim":[28],"leverage":[30],"high-quality":[32],"visio-linguistic":[33],"datasets":[34,183],"for":[35,95,163,210],"complementary":[37],"information":[38],"image":[40],"text":[42],"modalities.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47,99,195],"introduce":[48],"the":[49,120,125,133],"Wikipedia-based":[50],"Image":[51],"Text":[52],"(WIT)":[53],"Dataset":[54,207],"better":[56],"facilitate":[57],"multimodal,":[58],"multilingual":[59,141],"learning.":[60],"WIT":[61,87,110,118,138,167,186,206],"is":[62,119,139,208],"composed":[63],"of":[64,68,127,135,143,152,173],"a":[65,92,169,188,215],"curated":[66],"set":[67,172],"37.5":[69],"million":[70,77],"entity":[71],"rich":[72],"image-text":[73,108,128,200],"examples":[74,129],"with":[75,146],"11.5":[76],"unique":[78,115],"images":[79],"108":[81],"Wikipedia":[82],"languages.":[83],"Its":[84],"size":[85],"enables":[86],"be":[89],"used":[90],"as":[91,98,107,194,203],"pretraining":[93],"dataset":[94,123],"multimodal":[96,122],"models,":[97],"show":[100],"when":[101],"applied":[102],"tasks":[105],"such":[106],"retrieval.":[109],"has":[111,154],"four":[112],"main":[113],"advantages.":[116],"First,":[117],"largest":[121],"number":[126],"3x":[131],"(at":[132],"time":[134],"writing).":[136],"Second,":[137],"massively":[140],"(first":[142],"its":[144],"kind)":[145],"coverage":[147],"over":[148],"100+":[149],"languages":[150],"(each":[151],"which":[153],"at":[155],"least":[156],"12K":[157],"examples)":[158],"provides":[160,187],"cross-lingual":[161],"texts":[162],"many":[164],"images.":[165],"Third,":[166],"represents":[168],"more":[170],"diverse":[171],"concepts":[174],"real":[176],"world":[177],"entities":[178],"relative":[179],"what":[181],"previous":[182],"cover.":[184],"Lastly,":[185],"very":[189],"challenging":[190],"real-world":[191],"test":[192],"set,":[193],"empirically":[196],"illustrate":[197],"using":[198],"an":[199,204],"retrieval":[201],"task":[202],"example.":[205],"available":[209],"download":[211],"use":[213],"via":[214],"Creative":[216],"Commons":[217],"license":[218],"here:":[219],"https://github.com/google-research-datasets/wit.":[220]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":13}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}