{"id":"https://openalex.org/W1981565830","doi":"https://doi.org/10.14778/2078324.2078329","title":"Multilingual schema matching for Wikipedia infoboxes","display_name":"Multilingual schema matching for Wikipedia infoboxes","publication_year":2011,"publication_date":"2011-10-01","ids":{"openalex":"https://openalex.org/W1981565830","doi":"https://doi.org/10.14778/2078324.2078329","mag":"1981565830"},"language":"en","primary_location":{"id":"doi:10.14778/2078324.2078329","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2078324.2078329","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040718465","display_name":"Thanh Nguyen","orcid":"https://orcid.org/0009-0003-5122-2981"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Thanh Nguyen","raw_affiliation_strings":["University of Utah","University of Utah,"],"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"University of Utah,","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037408511","display_name":"Viviane P. Moreira","orcid":"https://orcid.org/0000-0003-4400-054X"},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Viviane Moreira","raw_affiliation_strings":["UFRGS-Brazil","UFRGS, Brazil#TAB#"],"affiliations":[{"raw_affiliation_string":"UFRGS-Brazil","institution_ids":["https://openalex.org/I130442723"]},{"raw_affiliation_string":"UFRGS, Brazil#TAB#","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055956330","display_name":"H. T. Nguyen","orcid":"https://orcid.org/0000-0002-7965-9742"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huong Nguyen","raw_affiliation_strings":["University of Utah","University of Utah,"],"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"University of Utah,","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101764273","display_name":"Hoa T. Nguyen","orcid":"https://orcid.org/0000-0001-6904-6312"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hoa Nguyen","raw_affiliation_strings":["University of Utah","University of Utah,"],"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"University of Utah,","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006773757","display_name":"Juliana Freire","orcid":"https://orcid.org/0000-0003-3915-7075"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juliana Freire","raw_affiliation_strings":["NYU Poly","NYU-Poly#TAB#"],"affiliations":[{"raw_affiliation_string":"NYU Poly","institution_ids":[]},{"raw_affiliation_string":"NYU-Poly#TAB#","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5040718465"],"corresponding_institution_ids":["https://openalex.org/I223532165"],"apc_list":null,"apc_paid":null,"fwci":4.7033,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.94688419,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"5","issue":"2","first_page":"133","last_page":"144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.9990000128746033,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8901205062866211},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5812518000602722},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.552024245262146},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.49537861347198486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49194666743278503},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.46180716156959534},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.421515554189682},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11775016784667969}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8901205062866211},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5812518000602722},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.552024245262146},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.49537861347198486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49194666743278503},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.46180716156959534},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.421515554189682},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11775016784667969}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/2078324.2078329","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2078324.2078329","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.370.77","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.370.77","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://vgc.poly.edu/~juliana/pub/wikimatch-vldb2012.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W15926365","https://openalex.org/W50119190","https://openalex.org/W58646613","https://openalex.org/W102708294","https://openalex.org/W1499239271","https://openalex.org/W1503434654","https://openalex.org/W1532325895","https://openalex.org/W1585939243","https://openalex.org/W1875032969","https://openalex.org/W1998982581","https://openalex.org/W2008896880","https://openalex.org/W2026051344","https://openalex.org/W2036073399","https://openalex.org/W2069870183","https://openalex.org/W2071424260","https://openalex.org/W2084176459","https://openalex.org/W2100408869","https://openalex.org/W2102239864","https://openalex.org/W2102872650","https://openalex.org/W2114558668","https://openalex.org/W2116363553","https://openalex.org/W2118966476","https://openalex.org/W2144870309","https://openalex.org/W2147152072","https://openalex.org/W2147982294","https://openalex.org/W2153508518","https://openalex.org/W2156543375","https://openalex.org/W2158246688","https://openalex.org/W2301772290","https://openalex.org/W2917259003","https://openalex.org/W4213009331","https://openalex.org/W4285719527","https://openalex.org/W4292081051"],"related_works":["https://openalex.org/W2775554247","https://openalex.org/W2250395065","https://openalex.org/W2110168585","https://openalex.org/W3107474891","https://openalex.org/W2250213760","https://openalex.org/W4386247111","https://openalex.org/W4327642362","https://openalex.org/W2587014613","https://openalex.org/W126620210","https://openalex.org/W2054406670"],"abstract_inverted_index":{"Recent":[0],"research":[1],"has":[2],"taken":[3],"advantage":[4],"of":[5,30,133,172],"Wikipedia's":[6],"multi-lingualism":[7],"as":[8,18,20],"a":[9,56,67,88,169,202],"resource":[10],"for":[11,23,40,69,120,222],"cross-language":[12,26],"information":[13],"retrieval":[14],"and":[15,45,125,148,177,191,220],"machine":[16],"translation,":[17],"well":[19],"proposed":[21],"techniques":[22],"enriching":[24],"its":[25],"structure.":[27],"The":[28,179],"availability":[29],"documents":[31],"in":[32,46,62,80,87,174,217],"multiple":[33],"languages":[34,121],"also":[35,118,195,200],"opens":[36],"up":[37],"new":[38],"opportunities":[39],"querying":[41],"structured":[42,223],"Wikipedia":[43,226],"content,":[44],"particular,":[47],"to":[48,108,154,214],"enable":[49],"answers":[50],"that":[51,76,122,137,157,182,207],"straddle":[52],"different":[53,81],"languages.":[54,82],"As":[55],"step":[57],"towards":[58],"supporting":[59],"such":[60],"queries,":[61],"this":[63],"paper,":[64],"we":[65,211],"propose":[66],"method":[68],"identifying":[70],"mappings":[71,86,110,210],"between":[72,111,145],"attributes":[73],"from":[74,78],"infoboxes":[75],"come":[77],"pages":[79,173],"Our":[83],"approach":[84,135,187],"finds":[85],"completely":[89],"automated":[90],"fashion.":[91],"Because":[92],"it":[93,99,105,116,138,150,194],"does":[94,139,185],"not":[95,102,140,183],"require":[96],"training":[97,128],"data,":[98],"is":[100,117,136],"scalable:":[101],"only":[103,184],"can":[104,151],"be":[106,152],"used":[107],"find":[109],"many":[112],"language":[113,155],"pairs,":[114],"but":[115,193],"effective":[119],"are":[123],"under-represented":[124],"lack":[126],"sufficient":[127],"samples.":[129],"Another":[130],"important":[131],"benefit":[132],"our":[134,186],"depend":[141],"on":[142],"syntactic":[143],"similarity":[144],"attribute":[146],"names,":[147],"thus,":[149],"applied":[153],"pairs":[156],"have":[158,162],"distinct":[159],"morphologies.":[160],"We":[161,199],"performed":[163],"an":[164],"extensive":[165],"experimental":[166],"evaluation":[167],"using":[168],"corpus":[170],"consisting":[171],"Portuguese,":[175],"Vietnamese,":[176],"English.":[178],"results":[180],"show":[181],"obtain":[188],"high":[189],"precision":[190],"recall,":[192],"outperforms":[196],"state-of-the-art":[197],"techniques.":[198],"present":[201],"case":[203],"study":[204],"which":[205],"demonstrates":[206],"the":[208],"multilingual":[209],"derive":[212],"lead":[213],"substantial":[215],"improvements":[216],"answer":[218],"quality":[219],"coverage":[221],"queries":[224],"over":[225],"content.":[227]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}