{"id":"https://openalex.org/W2399361902","doi":"https://doi.org/10.14778/2947618.2947624","title":"Comparative analysis of approximate blocking techniques for entity resolution","display_name":"Comparative analysis of approximate blocking techniques for entity resolution","publication_year":2016,"publication_date":"2016-05-01","ids":{"openalex":"https://openalex.org/W2399361902","doi":"https://doi.org/10.14778/2947618.2947624","mag":"2399361902"},"language":"en","primary_location":{"id":"doi:10.14778/2947618.2947624","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2947618.2947624","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/A5056976720","display_name":"George Papadakis","orcid":"https://orcid.org/0000-0002-7298-9431"},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"George Papadakis","raw_affiliation_strings":["University of Athens, Greece"],"affiliations":[{"raw_affiliation_string":"University of Athens, Greece","institution_ids":["https://openalex.org/I200777214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088094106","display_name":"Jonathan Svirsky","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jonathan Svirsky","raw_affiliation_strings":["Israel Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063111542","display_name":"Avigdor Gal","orcid":"https://orcid.org/0000-0002-7028-661X"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Avigdor Gal","raw_affiliation_strings":["Israel Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053726723","display_name":"Themis Palpanas","orcid":"https://orcid.org/0000-0002-8031-0265"},"institutions":[{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I110736937","display_name":"D\u00e9l\u00e9gation Paris 5","ror":"https://ror.org/02e0y6e06","country_code":"FR","type":"government","lineage":["https://openalex.org/I110736937","https://openalex.org/I154526488"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Themis Palpanas","raw_affiliation_strings":["Paris Descartes University, France"],"affiliations":[{"raw_affiliation_string":"Paris Descartes University, France","institution_ids":["https://openalex.org/I110736937","https://openalex.org/I204730241"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056976720"],"corresponding_institution_ids":["https://openalex.org/I200777214"],"apc_list":null,"apc_paid":null,"fwci":20.8811,"has_fulltext":false,"cited_by_count":169,"citation_normalized_percentile":{"value":0.99431091,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"9","issue":"9","first_page":"684","last_page":"695"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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":0.9919000267982483,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9804999828338623,"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/computer-science","display_name":"Computer science","score":0.7771091461181641},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.7279884815216064},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7150986194610596},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6951317191123962},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5030149817466736},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.446110337972641},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.19778165221214294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7771091461181641},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.7279884815216064},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7150986194610596},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6951317191123962},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5030149817466736},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.446110337972641},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.19778165221214294},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2947618.2947624","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2947618.2947624","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W192652968","https://openalex.org/W1485156179","https://openalex.org/W1540269031","https://openalex.org/W1976437052","https://openalex.org/W1997927541","https://openalex.org/W2011940398","https://openalex.org/W2024770506","https://openalex.org/W2031250218","https://openalex.org/W2036216970","https://openalex.org/W2041439319","https://openalex.org/W2073471108","https://openalex.org/W2073539176","https://openalex.org/W2079649893","https://openalex.org/W2104511295","https://openalex.org/W2108991785","https://openalex.org/W2111116800","https://openalex.org/W2117974736","https://openalex.org/W2128661986","https://openalex.org/W2129598390","https://openalex.org/W2132658991","https://openalex.org/W2142078760","https://openalex.org/W2151953639","https://openalex.org/W2152502401","https://openalex.org/W2161936973","https://openalex.org/W2210065635","https://openalex.org/W2271987422","https://openalex.org/W2397994241","https://openalex.org/W2398333000","https://openalex.org/W4254788633","https://openalex.org/W6632038546","https://openalex.org/W6683401941"],"related_works":["https://openalex.org/W2392835431","https://openalex.org/W1965371215","https://openalex.org/W2126932387","https://openalex.org/W1842396145","https://openalex.org/W2353762239","https://openalex.org/W2108990487","https://openalex.org/W2484966135","https://openalex.org/W2015050211","https://openalex.org/W2126435977","https://openalex.org/W3151146928"],"abstract_inverted_index":{"Entity":[0],"Resolution":[1],"is":[2,58,72],"a":[3,61,113],"core":[4],"task":[5],"for":[6],"merging":[7],"data":[8,22],"collections.":[9],"Due":[10],"to":[11,18,59,90,124],"its":[12],"quadratic":[13],"complexity,":[14],"it":[15],"typically":[16],"scales":[17],"large":[19],"volumes":[20],"of":[21,43,55,68,94,115],"through":[23],"blocking:":[24],"similar":[25],"entities":[26],"are":[27,34,48],"clustered":[28],"into":[29],"blocks":[30],"and":[31,52,84,98,104],"pair-wise":[32],"comparisons":[33],"executed":[35],"only":[36],"between":[37,102],"co-occurring":[38],"entities,":[39],"at":[40],"the":[41,53,66,76,92],"cost":[42],"some":[44],"missed":[45],"matches.":[46],"There":[47],"numerous":[49],"blocking":[50,82],"methods,":[51],"aim":[54],"this":[56],"work":[57],"offer":[60],"comprehensive":[62],"empirical":[63],"survey,":[64],"extending":[65],"dimensions":[67],"comparison":[69],"beyond":[70],"what":[71],"commonly":[73],"available":[74],"in":[75],"literature.":[77],"We":[78,107],"consider":[79],"17":[80],"state-of-the-art":[81],"methods":[83],"use":[85],"6":[86],"popular":[87],"real":[88],"datasets":[89,119],"examine":[91],"robustness":[93],"their":[95,99,110],"internal":[96],"configurations":[97],"relative":[100],"balance":[101],"effectiveness":[103],"time":[105],"efficiency.":[106],"also":[108],"investigate":[109],"scalability":[111],"over":[112],"corpus":[114],"7":[116],"established":[117],"synthetic":[118],"that":[120],"range":[121],"from":[122],"10,000":[123],"2":[125],"million":[126],"entities.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":33},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":26},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":1}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}