{"id":"https://openalex.org/W2168440643","doi":"https://doi.org/10.1109/tkde.2014.2359666","title":"Progressive Duplicate Detection","display_name":"Progressive Duplicate Detection","publication_year":2014,"publication_date":"2014-09-25","ids":{"openalex":"https://openalex.org/W2168440643","doi":"https://doi.org/10.1109/tkde.2014.2359666","mag":"2168440643"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2014.2359666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2014.2359666","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047144042","display_name":"Thorsten Papenbrock","orcid":"https://orcid.org/0000-0002-4019-8221"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thorsten Papenbrock","raw_affiliation_strings":["Department of Information Systems, Hasso-Plattner-Institute, Prof.-Dr.-Helmert-Str. 2-3, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, Hasso-Plattner-Institute, Prof.-Dr.-Helmert-Str. 2-3, Germany","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015327612","display_name":"Arvid Heise","orcid":null},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Arvid Heise","raw_affiliation_strings":["Department of Information Systems, Hasso-Plattner-Institute, Prof.-Dr.-Helmert-Str. 2-3, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, Hasso-Plattner-Institute, Prof.-Dr.-Helmert-Str. 2-3, Germany","institution_ids":["https://openalex.org/I143288331"]}]},{"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/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Naumann","raw_affiliation_strings":["Department of Information Systems, Hasso-Plattner-Institute, Prof.-Dr.-Helmert-Str. 2-3, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, Hasso-Plattner-Institute, Prof.-Dr.-Helmert-Str. 2-3, Germany","institution_ids":["https://openalex.org/I143288331"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I143288331"],"apc_list":null,"apc_paid":null,"fwci":11.5144,"has_fulltext":false,"cited_by_count":106,"citation_normalized_percentile":{"value":0.98654054,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"27","issue":"5","first_page":"1316","last_page":"1329"},"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":0.9916999936103821,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"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":0.8598307371139526},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6355030536651611},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5507413744926453},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.47219833731651306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8598307371139526},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6355030536651611},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5507413744926453},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.47219833731651306},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tkde.2014.2359666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2014.2359666","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:CiteSeerX.psu:10.1.1.979.2740","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.979.2740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hpi.de/fileadmin/user_upload/fachgebiete/naumann/publications/2014/ProgressiveDuplicateDetection.pdf","raw_type":"text"},{"id":"pmh:oai:www.openagrar.de:openagrar_mods_00111887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/TKDE.2014.2359666","pdf_url":null,"source":{"id":"https://openalex.org/S7407055137","display_name":"OpenAgrar","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":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W343945789","https://openalex.org/W1612155886","https://openalex.org/W1942676048","https://openalex.org/W1993091968","https://openalex.org/W1995099886","https://openalex.org/W1995541812","https://openalex.org/W2031250218","https://openalex.org/W2046020929","https://openalex.org/W2054633003","https://openalex.org/W2066792529","https://openalex.org/W2069897123","https://openalex.org/W2077044633","https://openalex.org/W2089711563","https://openalex.org/W2092336114","https://openalex.org/W2105436061","https://openalex.org/W2108087318","https://openalex.org/W2108991785","https://openalex.org/W2134295301","https://openalex.org/W2141634619","https://openalex.org/W2148524305","https://openalex.org/W2166988329","https://openalex.org/W2964250627","https://openalex.org/W3146259567","https://openalex.org/W4302802341","https://openalex.org/W6611560470","https://openalex.org/W6640432840"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W2352015183"],"abstract_inverted_index":{"Duplicate":[0],"detection":[1,16,43,96],"is":[2,57],"the":[3,29,48,54,61,64,68,89],"process":[4,20,66],"of":[5,9,31,50,63,93],"identifying":[6],"multiple":[7],"representations":[8],"same":[10],"real":[11],"world":[12],"entities.":[13],"Today,":[14],"duplicate":[15,42,95],"methods":[17],"need":[18],"to":[19],"ever":[21,25],"larger":[22],"datasets":[23],"in":[24],"shorter":[26],"time:":[27],"maintaining":[28],"quality":[30],"a":[32],"dataset":[33],"becomes":[34],"increasingly":[35],"difficult.":[36],"We":[37],"present":[38],"two":[39],"novel,":[40],"progressive":[41,85],"algorithms":[44,86],"that":[45,83],"significantly":[46,98],"increase":[47],"efficiency":[49,90],"finding":[51],"duplicates":[52],"if":[53],"execution":[55],"time":[56,69,92],"limited:":[58],"They":[59],"maximize":[60],"gain":[62],"overall":[65],"within":[67],"available":[70],"by":[71],"reporting":[72],"most":[73],"results":[74],"much":[75],"earlier":[76],"than":[77],"traditional":[78,94],"approaches.":[79],"Comprehensive":[80],"experiments":[81],"show":[82],"our":[84],"can":[87],"double":[88],"over":[91],"and":[97],"improve":[99],"upon":[100],"related":[101],"work.":[102]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
