{"id":"https://openalex.org/W2103734666","doi":"https://doi.org/10.1109/tkde.2014.2365779","title":"SERIMI: Class-Based Matching for Instance Matching Across Heterogeneous Datasets","display_name":"SERIMI: Class-Based Matching for Instance Matching Across Heterogeneous Datasets","publication_year":2014,"publication_date":"2014-10-30","ids":{"openalex":"https://openalex.org/W2103734666","doi":"https://doi.org/10.1109/tkde.2014.2365779","mag":"2103734666"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2014.2365779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2014.2365779","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ir.cwi.nl/pub/23443/23443D.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042016572","display_name":"Samur Ara\u00fajo","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Samur Araujo","raw_affiliation_strings":["Technical University of Delft, Delft, The Netherlands","Technical University of Delft, Delft, The Netherlands#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Delft, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Technical University of Delft, Delft, The Netherlands#TAB#","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029700870","display_name":"Duc Thanh Tran","orcid":"https://orcid.org/0000-0002-6873-7151"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Duc Thanh Tran","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany","Karlsruhe Institute of Technology, Karlsruhe,#N#Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe,#N#Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060259737","display_name":"Arjen P. de Vries","orcid":"https://orcid.org/0000-0002-2888-4202"},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832","https://openalex.org/I4405262988"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Arjen P. de Vries","raw_affiliation_strings":["Centrum Wiskunde & Informatica, Amsterdam, Netherlands","Centrum Wiskunde and Informatica, Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centrum Wiskunde & Informatica, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I1341640284"]},{"raw_affiliation_string":"Centrum Wiskunde and Informatica, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I1341640284"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089035049","display_name":"Daniel Schwabe","orcid":"https://orcid.org/0000-0003-4347-2940"},"institutions":[{"id":"https://openalex.org/I2699952","display_name":"Pontif\u00edcia Universidade Cat\u00f3lica do Rio de Janeiro","ror":"https://ror.org/01dg47b60","country_code":"BR","type":"education","lineage":["https://openalex.org/I2699952"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Daniel Schwabe","raw_affiliation_strings":["Department of Informatics, Pontifical Catholic University of Rio de Janeiro, Rio de Janeir, Brazil","[Department of Informatics, Pontifical Catholic University of Rio de Janeiro, Rio de Janeir, Brazil]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Pontifical Catholic University of Rio de Janeiro, Rio de Janeir, Brazil","institution_ids":["https://openalex.org/I2699952"]},{"raw_affiliation_string":"[Department of Informatics, Pontifical Catholic University of Rio de Janeiro, Rio de Janeir, Brazil]","institution_ids":["https://openalex.org/I2699952"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7011,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.93080494,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"27","issue":"5","first_page":"1397","last_page":"1440"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9909999966621399,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9829000234603882,"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":0.8252694010734558},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.8093660473823547},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6533535122871399},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5210953950881958},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4636036157608032},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.44981956481933594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41748669743537903},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3907485008239746},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08455222845077515}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8252694010734558},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.8093660473823547},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6533535122871399},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5210953950881958},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4636036157608032},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.44981956481933594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41748669743537903},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3907485008239746},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08455222845077515},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tkde.2014.2365779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2014.2365779","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:cwi.nl:23443","is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/23443","pdf_url":"https://ir.cwi.nl/pub/23443/23443D.pdf","source":{"id":"https://openalex.org/S7407055335","display_name":"Centrum Wiskunde & Informatica (CWI), the national research institute for mathematics and computer science in the Netherlands","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":"IEEE Transactions on Knowledge and Data Engineering vol. 27 no. 5, pp. 1397-1440","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:cwi.nl:23443","is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/23443","pdf_url":"https://ir.cwi.nl/pub/23443/23443D.pdf","source":{"id":"https://openalex.org/S7407055335","display_name":"Centrum Wiskunde & Informatica (CWI), the national research institute for mathematics and computer science in the Netherlands","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":"IEEE Transactions on Knowledge and Data Engineering vol. 27 no. 5, pp. 1397-1440","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2103734666.pdf","grobid_xml":"https://content.openalex.org/works/W2103734666.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W178573792","https://openalex.org/W1491268609","https://openalex.org/W1496571753","https://openalex.org/W1597082186","https://openalex.org/W1971684378","https://openalex.org/W2024770506","https://openalex.org/W2036216970","https://openalex.org/W2037594241","https://openalex.org/W2058469523","https://openalex.org/W2059975159","https://openalex.org/W2078797727","https://openalex.org/W2096742765","https://openalex.org/W2107799451","https://openalex.org/W2114764731","https://openalex.org/W2117054562","https://openalex.org/W2125980212","https://openalex.org/W2126890920","https://openalex.org/W2136930489","https://openalex.org/W2143124645","https://openalex.org/W2156510574","https://openalex.org/W2156543375","https://openalex.org/W2157896838","https://openalex.org/W2166733100","https://openalex.org/W2296113587","https://openalex.org/W2615115461","https://openalex.org/W2615447451","https://openalex.org/W2615982244","https://openalex.org/W2917757754","https://openalex.org/W4254788633","https://openalex.org/W6629365936","https://openalex.org/W6665389842","https://openalex.org/W6677401054","https://openalex.org/W6680962907","https://openalex.org/W6696834760","https://openalex.org/W6737878868","https://openalex.org/W6759494113"],"related_works":["https://openalex.org/W2033914206","https://openalex.org/W2146076056","https://openalex.org/W3121501642","https://openalex.org/W2163831990","https://openalex.org/W3003836766","https://openalex.org/W3124419391","https://openalex.org/W2169996322","https://openalex.org/W19461835","https://openalex.org/W2013728935","https://openalex.org/W2349046620"],"abstract_inverted_index":{"State-of-the-art":[0],"instance":[1],"matching":[2,11,44,94,152],"approaches":[3],"do":[4,103],"not":[5,46,104],"perform":[6],"well":[7],"when":[8,48],"used":[9],"for":[10],"instances":[12,33,38,73],"across":[13],"heterogeneous":[14],"datasets.":[15],"This":[16],"shortcoming":[17],"derives":[18],"from":[19,74,90],"their":[20],"core":[21],"operation":[22],"depending":[23],"on":[24,132,150],"direct":[25,30,123],"matching,":[26],"which":[27],"involves":[28],"a":[29,63,70,84],"comparison":[31,124],"of":[32,72,81,86,109,146],"in":[34,39,116],"the":[35,40,49,52,75,79,91,96,107,117,144],"source":[36,76,126],"with":[37],"target":[41,118,128],"dataset.":[42],"Direct":[43],"is":[45,54,119,129],"suitable":[47],"overlap":[50],"between":[51,125],"datasets":[53],"small.":[55],"Aiming":[56],"at":[57],"resolving":[58],"this":[59,112],"problem,":[60],"we":[61,138],"propose":[62],"new":[64],"paradigm":[65],"called":[66,78],"class-based":[67,93],"matching.":[68],"Given":[69],"class":[71,80,108],"dataset,":[77],"interest,":[82],"and":[83,127],"set":[85],"candidate":[87],"matches":[88],"retrieved":[89],"target,":[92],"refines":[95],"candidates":[97],"by":[98],"filtering":[99],"out":[100],"those":[101],"that":[102],"belong":[105],"to":[106],"interest.":[110],"For":[111],"refinement,":[113],"only":[114],"data":[115],"used,":[120],"i.e.,":[121],"no":[122],"involved.":[130],"Based":[131],"extensive":[133],"experiments":[134],"using":[135],"public":[136],"benchmarks,":[137],"show":[139],"our":[140],"approach":[141],"greatly":[142],"improves":[143],"quality":[145],"state-of-the-art":[147],"systems;":[148],"especially":[149],"difficult":[151],"tasks.":[153]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}