{"id":"https://openalex.org/W2112912553","doi":"https://doi.org/10.1109/dasfaa.2003.1192377","title":"Efficient record linkage in large data sets","display_name":"Efficient record linkage in large data sets","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2112912553","doi":"https://doi.org/10.1109/dasfaa.2003.1192377","mag":"2112912553"},"language":"en","primary_location":{"id":"doi:10.1109/dasfaa.2003.1192377","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dasfaa.2003.1192377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Eighth International Conference on Database Systems for Advanced Applications, 2003. (DASFAA 2003). Proceedings.","raw_type":"proceedings-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/A5042518722","display_name":"Liang Jin","orcid":"https://orcid.org/0000-0002-7552-7849"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Liang Jin","raw_affiliation_strings":["Department of Information and Computer Science, University of California, Irvine, CA, USA","Dept. of Inf. & Comput. Sci., California Univ., Irvine, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computer Science, University of California, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"Dept. of Inf. & Comput. Sci., California Univ., Irvine, CA, USA#TAB#","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369885","display_name":"Chen Li","orcid":"https://orcid.org/0000-0002-8784-8148"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Li","raw_affiliation_strings":["Department of Information and Computer Science, University of California, Irvine, CA, USA","Dept. of Inf. & Comput. Sci., California Univ., Irvine, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computer Science, University of California, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"Dept. of Inf. & Comput. Sci., California Univ., Irvine, CA, USA#TAB#","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010114060","display_name":"Sharad Mehrotra","orcid":"https://orcid.org/0000-0003-1667-5435"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Mehrotra","raw_affiliation_strings":["Department of Information and Computer Science, University of California, Irvine, CA, USA","Dept. of Inf. & Comput. Sci., California Univ., Irvine, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computer Science, University of California, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"Dept. of Inf. & Comput. Sci., California Univ., Irvine, CA, USA#TAB#","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5042518722"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":null,"apc_paid":null,"fwci":15.4778,"has_fulltext":false,"cited_by_count":173,"citation_normalized_percentile":{"value":0.99263412,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"137","last_page":"146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T11106","display_name":"Data Management and Algorithms","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9842000007629395,"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/merge","display_name":"Merge (version control)","score":0.7371570467948914},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6992201209068298},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.658535897731781},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6094195246696472},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5227456092834473},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.5026364326477051},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4433292746543884},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.4278523623943329},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4115886688232422},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2962324023246765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23470079898834229},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1049593985080719},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07104545831680298}],"concepts":[{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.7371570467948914},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6992201209068298},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.658535897731781},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6094195246696472},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5227456092834473},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.5026364326477051},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4433292746543884},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.4278523623943329},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4115886688232422},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2962324023246765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23470079898834229},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1049593985080719},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07104545831680298},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/dasfaa.2003.1192377","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dasfaa.2003.1192377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Eighth International Conference on Database Systems for Advanced Applications, 2003. (DASFAA 2003). Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.11.5015","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.11.5015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ics.uci.edu/~chenli/pub/linkage.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.11.8132","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.11.8132","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ics.uci.edu/~chenli/pub/dasfaa03.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1485156179","https://openalex.org/W1583581687","https://openalex.org/W1647671624","https://openalex.org/W2001907516","https://openalex.org/W2010595692","https://openalex.org/W2014879296","https://openalex.org/W2024770506","https://openalex.org/W2041884394","https://openalex.org/W2045235113","https://openalex.org/W2046144220","https://openalex.org/W2058903936","https://openalex.org/W2059378307","https://openalex.org/W2063491776","https://openalex.org/W2072145795","https://openalex.org/W2085099553","https://openalex.org/W2106895292","https://openalex.org/W2112173399","https://openalex.org/W2123060058","https://openalex.org/W2135527206","https://openalex.org/W2153516438","https://openalex.org/W2153977007","https://openalex.org/W2161600801","https://openalex.org/W2161936973","https://openalex.org/W2167081989","https://openalex.org/W2168532702","https://openalex.org/W2542460421","https://openalex.org/W2752885492","https://openalex.org/W3015571647","https://openalex.org/W4246354968","https://openalex.org/W4254788633","https://openalex.org/W6628896031","https://openalex.org/W6636915900","https://openalex.org/W6676014748","https://openalex.org/W6683401941","https://openalex.org/W6684612202"],"related_works":["https://openalex.org/W2487032012","https://openalex.org/W2211355040","https://openalex.org/W2808916796","https://openalex.org/W2176311362","https://openalex.org/W3012491082","https://openalex.org/W2019538911","https://openalex.org/W2467200550","https://openalex.org/W1996805379","https://openalex.org/W4234584818","https://openalex.org/W3211905090"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"an":[3,104],"efficient":[4],"approach":[5,69,102],"to":[6,25,70,82,139],"record":[7],"linkage.":[8],"Given":[9,106],"two":[10,33,113],"lists":[11],"of":[12,18,55,76,119,143],"records,":[13,77],"the":[14,29,45,53,100,107,125,134],"record-linkage":[15,48],"problem":[16,49],"consists":[17],"determining":[19],"all":[20],"pairs":[21,142],"that":[22,58,87,110,153],"are":[23,115,121],"similar":[24,141],"each":[26,74],"other":[27],"where":[28],"overall":[30],"similarity":[31,131],"between":[32],"records":[34,114],"is":[35,137],"defined":[36],"based":[37],"on":[38],"domain-specific":[39,89],"similarities":[40],"over":[41,133],"individual":[42],"attributes":[43,120,136],"constituting":[44],"record.":[46],"The":[47],"arises":[50],"naturally":[51],"in":[52],"context":[54],"data":[56,61,150],"cleansing":[57],"usually":[59],"precedes":[60],"analysis":[62],"and":[63,97,160],"mining.":[64],"We":[65],"explore":[66],"a":[67,83,117],"novel":[68],"this":[71],"problem.":[72],"For":[73],"attribute":[75],"we":[78,98],"first":[79],"map":[80],"values":[81],"multidimensional":[84,130],"Euclidean":[85],"space":[86],"preserves":[88],"similarity.":[90],"Many":[91],"mapping":[92],"algorithms":[93],"can":[94],"be":[95],"applied,":[96],"use":[99],"FastMap":[101],"as":[103],"example.":[105],"merging":[108],"rule":[109],"defines":[111],"when":[112],"Similar":[116],"set":[118],"chosen":[122,135],"along":[123],"which":[124],"merge":[126],"will":[127],"proceed":[128],"A":[129],"join":[132],"used":[138],"determine":[140],"records.":[144],"Our":[145],"extensive":[146],"experiments":[147],"using":[148],"real":[149],"sets":[151],"show":[152],"our":[154],"solution":[155],"has":[156],"very":[157],"good":[158],"efficiency":[159],"accuracy.":[161]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}