{"id":"https://openalex.org/W2058151452","doi":"https://doi.org/10.1145/2422604.2422607","title":"RUBIX","display_name":"RUBIX","publication_year":2012,"publication_date":"2012-05-25","ids":{"openalex":"https://openalex.org/W2058151452","doi":"https://doi.org/10.1145/2422604.2422607","mag":"2058151452"},"language":"en","primary_location":{"id":"doi:10.1145/2422604.2422607","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2422604.2422607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First International Workshop on Open Data","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-00823583","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050129866","display_name":"Ahmad Assaf","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133526","display_name":"Centre Azur\u00e9en de Canc\u00e9rologie","ror":"https://ror.org/03edm8e08","country_code":"FR","type":"healthcare","lineage":["https://openalex.org/I4210133526"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ahmad Assaf","raw_affiliation_strings":["SAP Research, Mougins Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAP Research, Mougins Cedex, France","institution_ids":["https://openalex.org/I4210133526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070017359","display_name":"Eldad Louw","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133526","display_name":"Centre Azur\u00e9en de Canc\u00e9rologie","ror":"https://ror.org/03edm8e08","country_code":"FR","type":"healthcare","lineage":["https://openalex.org/I4210133526"]},{"id":"https://openalex.org/I4210135152","display_name":"Roland Ernst Stiftung","ror":"https://ror.org/03m629g08","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210135152"]}],"countries":["DE","FR"],"is_corresponding":false,"raw_author_name":"Eldad Louw","raw_affiliation_strings":["SAP Research, Mougins Cedex, France","SAP Research [Dresden] (SAP Research CEC Dresden; Chemnitzer Strasse 48; 01187 Dresden; Germany - Germany)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAP Research, Mougins Cedex, France","institution_ids":["https://openalex.org/I4210133526"]},{"raw_affiliation_string":"SAP Research [Dresden] (SAP Research CEC Dresden; Chemnitzer Strasse 48; 01187 Dresden; Germany - Germany)","institution_ids":["https://openalex.org/I4210135152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027271719","display_name":"Aline Senart","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133526","display_name":"Centre Azur\u00e9en de Canc\u00e9rologie","ror":"https://ror.org/03edm8e08","country_code":"FR","type":"healthcare","lineage":["https://openalex.org/I4210133526"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Aline Senart","raw_affiliation_strings":["SAP Research, Mougins Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAP Research, Mougins Cedex, France","institution_ids":["https://openalex.org/I4210133526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053158530","display_name":"Corentin Follenfant","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133526","display_name":"Centre Azur\u00e9en de Canc\u00e9rologie","ror":"https://ror.org/03edm8e08","country_code":"FR","type":"healthcare","lineage":["https://openalex.org/I4210133526"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Corentin Follenfant","raw_affiliation_strings":["SAP Research, Mougins Cedex, France","SAP Research [Sophia Antipolis] (805 Avenue du Docteur Maurice Donat, BP1216-06254 Mougins, France - France)","WIMMICS - Web-Instrumented Man-Machine Interactions, Communities and Semantics (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAP Research, Mougins Cedex, France","institution_ids":["https://openalex.org/I4210133526"]},{"raw_affiliation_string":"SAP Research [Sophia Antipolis] (805 Avenue du Docteur Maurice Donat, BP1216-06254 Mougins, France - France)","institution_ids":[]},{"raw_affiliation_string":"WIMMICS - Web-Instrumented Man-Machine Interactions, Communities and Semantics (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022574838","display_name":"Rapha\u00ebl Troncy","orcid":"https://orcid.org/0000-0003-0457-1436"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Rapha\u00ebl Troncy","raw_affiliation_strings":["EURECOM, Sophia Antipolis, France","Eurecom [Sophia Antipolis] (Campus SophiaTech, 450 Route des Chappes, CS 50193 - 06904 Biot Sophia Antipolis cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EURECOM, Sophia Antipolis, France","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"Eurecom [Sophia Antipolis] (Campus SophiaTech, 450 Route des Chappes, CS 50193 - 06904 Biot Sophia Antipolis cedex - France)","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016534223","display_name":"David Trastour","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133526","display_name":"Centre Azur\u00e9en de Canc\u00e9rologie","ror":"https://ror.org/03edm8e08","country_code":"FR","type":"healthcare","lineage":["https://openalex.org/I4210133526"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"David Trastour","raw_affiliation_strings":["SAP Research, Mougins Cedex, France","SAP Research [Sophia Antipolis] (805 Avenue du Docteur Maurice Donat, BP1216-06254 Mougins, France - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAP Research, Mougins Cedex, France","institution_ids":["https://openalex.org/I4210133526"]},{"raw_affiliation_string":"SAP Research [Sophia Antipolis] (805 Avenue du Docteur Maurice Donat, BP1216-06254 Mougins, France - France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","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/T12016","display_name":"Web Data Mining and Analysis","score":0.9987000226974487,"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":0.8510817289352417},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.7199256420135498},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5458271503448486},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.5217491388320923},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5037502646446228},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4732136130332947},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.4664174020290375},{"id":"https://openalex.org/keywords/business-intelligence","display_name":"Business intelligence","score":0.4571211040019989},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4435121715068817},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.43476784229278564},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.42907774448394775},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3267718553543091},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.11485236883163452}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8510817289352417},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.7199256420135498},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5458271503448486},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.5217491388320923},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5037502646446228},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4732136130332947},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.4664174020290375},{"id":"https://openalex.org/C2767350","wikidata":"https://www.wikidata.org/wiki/Q6662173","display_name":"Business intelligence","level":2,"score":0.4571211040019989},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4435121715068817},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.43476784229278564},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.42907774448394775},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3267718553543091},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.11485236883163452},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2422604.2422607","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2422604.2422607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First International Workshop on Open Data","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-00823583v1","is_oa":true,"landing_page_url":"https://hal.science/hal-00823583","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"WOD '12 Proceedings of the First International Workshop on Open Data, May 2012, France. pp.13-21, &#x27E8;10.1145/2422604.2422607&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00823583v1","is_oa":true,"landing_page_url":"https://hal.science/hal-00823583","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"WOD '12 Proceedings of the First International Workshop on Open Data, May 2012, France. pp.13-21, &#x27E8;10.1145/2422604.2422607&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W102708294","https://openalex.org/W1501251778","https://openalex.org/W1505139855","https://openalex.org/W1519485861","https://openalex.org/W1580755323","https://openalex.org/W1867850975","https://openalex.org/W1988674507","https://openalex.org/W2015191210","https://openalex.org/W2022166150","https://openalex.org/W2069388662","https://openalex.org/W2111869785","https://openalex.org/W2127812868","https://openalex.org/W2129595335","https://openalex.org/W2144948358","https://openalex.org/W2158698691","https://openalex.org/W2404643063","https://openalex.org/W2407880898","https://openalex.org/W2736054604","https://openalex.org/W2796218018"],"related_works":["https://openalex.org/W208715492","https://openalex.org/W2581040172","https://openalex.org/W2383696629","https://openalex.org/W2506063602","https://openalex.org/W23190051","https://openalex.org/W2362581214","https://openalex.org/W2384379346","https://openalex.org/W3165010183","https://openalex.org/W2953652248","https://openalex.org/W2901498424"],"abstract_inverted_index":{"With":[0],"today's":[1],"public":[2],"data":[3,8,19,24,32,37,62],"sets":[4],"containing":[5],"billions":[6],"of":[7,108],"items,":[9],"more":[10,12,117],"and":[11,39,41,99,112],"companies":[13],"are":[14],"looking":[15],"to":[16,25,59,74,93,116],"integrate":[17],"external":[18],"with":[20,77,97,102],"their":[21],"traditional":[22],"enterprise":[23],"improve":[26],"business":[27,57],"intelligence":[28],"analysis.":[29],"These":[30],"distributed":[31],"sources":[33],"however":[34],"exhibit":[35],"heterogeneous":[36],"formats":[38],"terminologies":[40],"may":[42],"contain":[43],"noisy":[44,66],"data.":[45,68],"In":[46],"this":[47],"paper,":[48],"we":[49],"present":[50],"RUBIX,":[51],"a":[52],"novel":[53,78],"framework":[54,70],"that":[55,89],"enables":[56],"users":[58],"semi-automatically":[60],"perform":[61],"integration":[63],"on":[64],"potentially":[65],"tabular":[67],"This":[69],"offers":[71],"an":[72],"extension":[73],"Google":[75],"Refine":[76],"schema":[79],"matching":[80,110],"algorithms":[81],"leveraging":[82],"Freebase":[83],"rich":[84],"types.":[85],"First":[86],"experiments":[87],"show":[88],"using":[90],"Linked":[91],"Data":[92],"map":[94],"cell":[95],"values":[96],"instances":[98],"column":[100],"headers":[101],"types":[103],"improves":[104],"significantly":[105],"the":[106,109],"quality":[107],"results":[111],"therefore":[113],"should":[114],"lead":[115],"informed":[118],"decisions.":[119]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2016-06-24T00:00:00"}
