{"id":"https://openalex.org/W3008440336","doi":"https://doi.org/10.14778/3377369.3377379","title":"MDedup","display_name":"MDedup","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3008440336","doi":"https://doi.org/10.14778/3377369.3377379","mag":"3008440336"},"language":"en","primary_location":{"id":"doi:10.14778/3377369.3377379","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3377369.3377379","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/A5016557675","display_name":"loannis Koumarelas","orcid":null},"institutions":[{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"loannis Koumarelas","raw_affiliation_strings":["University of Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Potsdam, Germany","institution_ids":["https://openalex.org/I176453806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047144042","display_name":"Thorsten Papenbrock","orcid":"https://orcid.org/0000-0002-4019-8221"},"institutions":[{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thorsten Papenbrock","raw_affiliation_strings":["University of Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Potsdam, Germany","institution_ids":["https://openalex.org/I176453806"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053028480","display_name":"Felix Naumann","orcid":"https://orcid.org/0000-0002-4483-1389"},"institutions":[{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Naumann","raw_affiliation_strings":["University of Potsdam, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Potsdam, Germany","institution_ids":["https://openalex.org/I176453806"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I176453806"],"apc_list":null,"apc_paid":null,"fwci":1.9439,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.86338013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"13","issue":"5","first_page":"712","last_page":"725"},"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":0.9869999885559082,"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/T10582","display_name":"Ethics in Clinical Research","score":0.910099983215332,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8026522397994995},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5828546285629272},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5629112720489502},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5109821557998657},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4848938584327698},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4428223967552185},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4193493127822876},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.347007691860199},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08821633458137512}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8026522397994995},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5828546285629272},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5629112720489502},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5109821557998657},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4848938584327698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4428223967552185},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4193493127822876},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.347007691860199},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08821633458137512},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/3377369.3377379","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3377369.3377379","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:kobv.de-opus4-uni-potsdam:56988","is_oa":false,"landing_page_url":"https://publishup.uni-potsdam.de/frontdoor/index/index/docId/56988","pdf_url":null,"source":{"id":"https://openalex.org/S4377196346","display_name":"publish.UP (University of Potsdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I176453806","host_organization_name":"University of Potsdam","host_organization_lineage":["https://openalex.org/I176453806"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.46000000834465027,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1546961578","https://openalex.org/W1547612978","https://openalex.org/W1582775886","https://openalex.org/W1647671624","https://openalex.org/W1702887526","https://openalex.org/W2035615211","https://openalex.org/W2059009730","https://openalex.org/W2065199439","https://openalex.org/W2069728146","https://openalex.org/W2079649893","https://openalex.org/W2100986433","https://openalex.org/W2104511295","https://openalex.org/W2108991785","https://openalex.org/W2109943925","https://openalex.org/W2114764731","https://openalex.org/W2145346822","https://openalex.org/W2157963512","https://openalex.org/W2164456230","https://openalex.org/W2167011595","https://openalex.org/W2186686397","https://openalex.org/W2237543400","https://openalex.org/W2596356468","https://openalex.org/W2621384249","https://openalex.org/W2674513843","https://openalex.org/W2769041395","https://openalex.org/W2775696413","https://openalex.org/W2793768458","https://openalex.org/W2798649495","https://openalex.org/W2889353337","https://openalex.org/W2957204582","https://openalex.org/W2959716049","https://openalex.org/W2997181101","https://openalex.org/W3011807731","https://openalex.org/W3023590196","https://openalex.org/W3099883947","https://openalex.org/W4285719527","https://openalex.org/W6637786517","https://openalex.org/W6677894765"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W1549363203","https://openalex.org/W4231274751","https://openalex.org/W2154063878","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W1518215897","https://openalex.org/W1538046993","https://openalex.org/W1566995892"],"abstract_inverted_index":{"Duplicate":[0],"detection":[1,24,78,109,121],"is":[2,55,81],"an":[3,139],"integral":[4],"part":[5],"of":[6,15,39,132],"data":[7,134],"cleaning":[8,135],"and":[9,45,74,96,154],"serves":[10],"to":[11,33,63,100,151],"identify":[12],"multiple":[13],"representations":[14],"same":[16],"real-world":[17],"entities":[18],"in":[19],"(relational)":[20],"datasets.":[21],"Existing":[22],"duplicate":[23,77,108,120],"approaches":[25],"are":[26,30,47,162],"effective,":[27],"but":[28],"they":[29],"also":[31],"hard":[32],"parameterize":[34],"or":[35,173],"require":[36,171],"a":[37,56,59,71,102],"lot":[38],"pre-labeled":[40],"training":[41],"data.":[42],"Both":[43],"parameterization":[44],"pre-labeling":[46],"at":[48],"least":[49],"domain-specific":[50],"if":[51,58],"not":[52,170],"dataset-specific,":[53],"which":[54,161],"problem":[57],"new":[60,124],"dataset":[61,94],"needs":[62],"be":[64],"cleaned.":[65],"For":[66],"this":[67,147],"reason,":[68],"we":[69,137],"propose":[70,138],"novel,":[72],"rule-based":[73],"fully":[75],"automatic":[76],"approach":[79,148],"that":[80,104,146,166],"based":[82],"on":[83,122,157],"matching":[84],"dependencies":[85],"(MDs).":[86],"Our":[87,143],"system":[88,168],"uses":[89],"automatically":[90],"discovered":[91],"MDs,":[92],"various":[93],"features,":[95],"known":[97],"gold":[98],"standards":[99],"train":[101],"model":[103,114],"selects":[105],"MDs":[106,118],"as":[107],"rules.":[110],"Once":[111],"trained,":[112],"the":[113,128,167],"can":[115],"select":[116],"useful":[117],"for":[119],"any":[123],"dataset.":[125],"To":[126],"increase":[127],"generally":[129],"low":[130],"recall":[131],"MD-based":[133],"approaches,":[136],"additional":[140],"boosting":[141],"step.":[142],"experiments":[144],"show":[145],"reaches":[149],"up":[150],"94%":[152],"F-measure":[153],"100%":[155],"precision":[156],"our":[158],"evaluation":[159],"datasets,":[160],"good":[163],"numbers":[164],"considering":[165],"does":[169],"domain":[172],"target":[174],"data-specific":[175],"configuration.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2020-03-06T00:00:00"}