{"id":"https://openalex.org/W2119225321","doi":"https://doi.org/10.1145/1141753.1141760","title":"Learning to deduplicate","display_name":"Learning to deduplicate","publication_year":2006,"publication_date":"2006-06-11","ids":{"openalex":"https://openalex.org/W2119225321","doi":"https://doi.org/10.1145/1141753.1141760","mag":"2119225321"},"language":"en","primary_location":{"id":"doi:10.1145/1141753.1141760","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141753.1141760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM/IEEE-CS joint conference on Digital libraries","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/A5023888691","display_name":"Mois\u00e9s G. de Carvalho","orcid":null},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Mois\u00e9s G. de Carvalho","raw_affiliation_strings":["Federal University of Minas Gerais, Belo Horizonte, Brazil","Federal University of Minas Gerais, Belo Horizonte; Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]},{"raw_affiliation_string":"Federal University of Minas Gerais, Belo Horizonte; Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046370637","display_name":"Marcos Andr\u00e9 Gon\u00e7alves","orcid":"https://orcid.org/0000-0002-2075-3363"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcos Andr\u00e9 Gon\u00e7alves","raw_affiliation_strings":["Federal University of Minas Gerais, Belo Horizonte, Brazil","Federal University of Minas Gerais, Belo Horizonte; Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]},{"raw_affiliation_string":"Federal University of Minas Gerais, Belo Horizonte; Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045978751","display_name":"Alberto H. F. Laender","orcid":"https://orcid.org/0000-0001-5032-2233"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Alberto H. F. Laender","raw_affiliation_strings":["Federal University of Minas Gerais, Belo Horizonte, Brazil","Federal University of Minas Gerais, Belo Horizonte; Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]},{"raw_affiliation_string":"Federal University of Minas Gerais, Belo Horizonte; Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015763962","display_name":"Altigran S. da Silva","orcid":null},"institutions":[{"id":"https://openalex.org/I62885914","display_name":"Universidade Federal do Amazonas","ror":"https://ror.org/02263ky35","country_code":"BR","type":"education","lineage":["https://openalex.org/I62885914"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Altigran S. da Silva","raw_affiliation_strings":["Federal University of Amazonas, Manaus, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Amazonas, Manaus, Brazil","institution_ids":["https://openalex.org/I62885914"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.335,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.9397263,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"50"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.992900013923645,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9679999947547913,"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/data-deduplication","display_name":"Data deduplication","score":0.9190279245376587},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8263401985168457},{"id":"https://openalex.org/keywords/genetic-programming","display_name":"Genetic programming","score":0.6712279319763184},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5872315168380737},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5865822434425354},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5487653613090515},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49808716773986816},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.48634177446365356},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2870640754699707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26845139265060425},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20845526456832886}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9190279245376587},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8263401985168457},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.6712279319763184},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5872315168380737},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5865822434425354},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5487653613090515},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49808716773986816},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.48634177446365356},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2870640754699707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26845139265060425},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20845526456832886},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1141753.1141760","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141753.1141760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1576818901","https://openalex.org/W1660390307","https://openalex.org/W1969056935","https://openalex.org/W2052581258","https://openalex.org/W2059035258","https://openalex.org/W2073471108","https://openalex.org/W2100604298","https://openalex.org/W2105423800","https://openalex.org/W2105484782","https://openalex.org/W2127674618","https://openalex.org/W2135223301","https://openalex.org/W2154498027","https://openalex.org/W2154785834","https://openalex.org/W2162495634","https://openalex.org/W2164456230","https://openalex.org/W2170902582","https://openalex.org/W6669040500"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W2943088381","https://openalex.org/W4296125805","https://openalex.org/W4385804830","https://openalex.org/W2144348063","https://openalex.org/W2074021203","https://openalex.org/W1982579475"],"abstract_inverted_index":{"Identifying":[0],"record":[1,97,117],"replicas":[2,98,155],"in":[3,99,119,156,169],"Digital":[4],"Libraries":[5],"and":[6,21,109,147,164],"other":[7],"types":[8],"of":[9,18,38,62,134],"digital":[10],"repositories":[11],"is":[12,88],"fundamental":[13],"to":[14,26,45,49,90,95,121],"improve":[15],"the":[16,60,78,111,116,128,135,142],"quality":[17],"their":[19],"content":[20],"services":[22],"as":[23,25,52],"well":[24],"yield":[27],"eventual":[28],"sharing":[29],"efforts.":[30],"Several":[31],"deduplication":[32,79],"strategies":[33],"are":[34],"available,":[35],"but":[36],"most":[37],"them":[39],"rely":[40],"on":[41,84],"manually":[42],"chosen":[43],"settings":[44],"combine":[46,108],"evidence":[47,113],"used":[48],"identify":[50,96],"records":[51,126],"being":[53],"replicas.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58,64,74],"present":[59],"results":[61,133],"experiments":[63,136],"have":[65,75],"carried":[66],"out":[67],"with":[68,173],"a":[69,100,157,170],"novel":[70],"Machine":[71],"Learning":[72],"approach":[73,140],"proposed":[76],"for":[77],"problem.":[80],"This":[81],"approach,":[82],"based":[83],"Genetic":[85],"Programming":[86],"(GP),":[87],"able":[89],"automatically":[91],"generate":[92],"similarity":[93,105],"functions":[94,106],"given":[101],"repository.":[102],"The":[103,132],"generated":[104],"properly":[107],"weight":[110],"best":[112],"available":[114],"among":[115],"fields":[118],"order":[120],"tell":[122],"when":[123,153],"two":[124],"distinct":[125],"represent":[127],"same":[129],"real-world":[130],"entity.":[131],"show":[137],"that":[138],"our":[139],"outperforms":[141],"baseline":[143],"method":[144],"by":[145,149,165],"Fellegi":[146],"Sunter":[148],"more":[150,166],"than":[151,167],"12%":[152],"identifying":[154],"data":[158,171],"set":[159,172],"containing":[160],"researcher's":[161],"personal":[162],"data,":[163],"7%,":[168],"article":[174],"citation":[175],"data.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}