{"id":"https://openalex.org/W3014295153","doi":"https://doi.org/10.1145/3377455","title":"Blocking and Filtering Techniques for Entity Resolution","display_name":"Blocking and Filtering Techniques for Entity Resolution","publication_year":2020,"publication_date":"2020-03-20","ids":{"openalex":"https://openalex.org/W3014295153","doi":"https://doi.org/10.1145/3377455","mag":"3014295153"},"language":"en","primary_location":{"id":"doi:10.1145/3377455","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3377455","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"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":"ACM Computing Surveys","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://lirias.kuleuven.be/retrieve/99bbead1-8834-49e9-84da-a68a3d563da6","any_repository_has_fulltext":true},"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":false,"raw_author_name":"George Papadakis","raw_affiliation_strings":["University of Athens, Greece"],"raw_orcid":"https://orcid.org/0000-0002-7298-9431","affiliations":[{"raw_affiliation_string":"University of Athens, Greece","institution_ids":["https://openalex.org/I200777214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087768208","display_name":"Dimitrios Skoutas","orcid":"https://orcid.org/0000-0002-6118-5227"},"institutions":[{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Dimitrios Skoutas","raw_affiliation_strings":["IMSI, Athena Research Center, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IMSI, Athena Research Center, Greece","institution_ids":["https://openalex.org/I4210156054"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029636071","display_name":"Emmanouil Thanos","orcid":"https://orcid.org/0000-0002-9218-5027"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Emmanouil Thanos","raw_affiliation_strings":["KU Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KU Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"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/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"]},{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Themis Palpanas","raw_affiliation_strings":["Paris Descartes University, France"],"raw_orcid":null,"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":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.4948,"has_fulltext":true,"cited_by_count":197,"citation_normalized_percentile":{"value":0.99508238,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"53","issue":"2","first_page":"1","last_page":"42"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9891999959945679,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9887999892234802,"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":0.8966678380966187},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.7580081820487976},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6276265382766724},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5557142496109009},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5401517152786255},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.47314131259918213},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4716574251651764},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.4323580265045166},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43017587065696716},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4127194583415985},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33223679661750793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29082685708999634},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11403846740722656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8966678380966187},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.7580081820487976},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6276265382766724},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5557142496109009},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5401517152786255},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.47314131259918213},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4716574251651764},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.4323580265045166},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43017587065696716},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4127194583415985},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33223679661750793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29082685708999634},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11403846740722656},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3377455","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3377455","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"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":"ACM Computing Surveys","raw_type":"journal-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/663504","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/663504","pdf_url":"https://lirias.kuleuven.be/retrieve/99bbead1-8834-49e9-84da-a68a3d563da6","source":{"id":"https://openalex.org/S7407055369","display_name":"Lirias","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Acm Computing Surveys, vol. 53 (2), Art.No. ARTN 31","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/663504","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/663504","pdf_url":"https://lirias.kuleuven.be/retrieve/99bbead1-8834-49e9-84da-a68a3d563da6","source":{"id":"https://openalex.org/S7407055369","display_name":"Lirias","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Acm Computing Surveys, vol. 53 (2), Art.No. ARTN 31","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3791724392","display_name":null,"funder_award_id":"825041","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G6039968272","display_name":null,"funder_award_id":"825258","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G7331901853","display_name":null,"funder_award_id":"EU H2020","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3014295153.pdf","grobid_xml":"https://content.openalex.org/works/W3014295153.grobid-xml"},"referenced_works_count":199,"referenced_works":["https://openalex.org/W20290297","https://openalex.org/W31497229","https://openalex.org/W55416716","https://openalex.org/W69311973","https://openalex.org/W87992039","https://openalex.org/W1155226818","https://openalex.org/W1502916507","https://openalex.org/W1504263697","https://openalex.org/W1540269031","https://openalex.org/W1547612978","https://openalex.org/W1612155886","https://openalex.org/W1724849505","https://openalex.org/W1845040079","https://openalex.org/W1870428314","https://openalex.org/W1874327257","https://openalex.org/W1910093137","https://openalex.org/W1956625581","https://openalex.org/W1964189668","https://openalex.org/W1973001156","https://openalex.org/W1976437052","https://openalex.org/W1981590391","https://openalex.org/W1982538504","https://openalex.org/W1982859875","https://openalex.org/W1985558865","https://openalex.org/W1986017822","https://openalex.org/W1990947147","https://openalex.org/W1992930793","https://openalex.org/W1993997820","https://openalex.org/W1994229028","https://openalex.org/W1997927541","https://openalex.org/W2005320059","https://openalex.org/W2008565899","https://openalex.org/W2011940398","https://openalex.org/W2017167478","https://openalex.org/W2019150658","https://openalex.org/W2019412213","https://openalex.org/W2024386211","https://openalex.org/W2024770506","https://openalex.org/W2029128277","https://openalex.org/W2031250218","https://openalex.org/W2035835285","https://openalex.org/W2036216970","https://openalex.org/W2037562342","https://openalex.org/W2039657250","https://openalex.org/W2041439319","https://openalex.org/W2042458413","https://openalex.org/W2047940964","https://openalex.org/W2058733945","https://openalex.org/W2062716225","https://openalex.org/W2069728146","https://openalex.org/W2070162726","https://openalex.org/W2073167797","https://openalex.org/W2073471108","https://openalex.org/W2073539176","https://openalex.org/W2074526732","https://openalex.org/W2077044633","https://openalex.org/W2079649893","https://openalex.org/W2088008685","https://openalex.org/W2092336114","https://openalex.org/W2093270024","https://openalex.org/W2096598900","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2100548092","https://openalex.org/W2103734666","https://openalex.org/W2105016630","https://openalex.org/W2105436061","https://openalex.org/W2107799451","https://openalex.org/W2108087318","https://openalex.org/W2109834209","https://openalex.org/W2111116800","https://openalex.org/W2115214414","https://openalex.org/W2117974736","https://openalex.org/W2121269638","https://openalex.org/W2121287775","https://openalex.org/W2121516976","https://openalex.org/W2123561513","https://openalex.org/W2127675794","https://openalex.org/W2128661986","https://openalex.org/W2132069633","https://openalex.org/W2132658991","https://openalex.org/W2139490252","https://openalex.org/W2139646386","https://openalex.org/W2139929608","https://openalex.org/W2142787640","https://openalex.org/W2147299132","https://openalex.org/W2148148676","https://openalex.org/W2150916025","https://openalex.org/W2151930506","https://openalex.org/W2152502401","https://openalex.org/W2153579005","https://openalex.org/W2155502235","https://openalex.org/W2156855109","https://openalex.org/W2158047102","https://openalex.org/W2158418361","https://openalex.org/W2161936973","https://openalex.org/W2162006472","https://openalex.org/W2163616098","https://openalex.org/W2164456230","https://openalex.org/W2166400748","https://openalex.org/W2166733100","https://openalex.org/W2166988329","https://openalex.org/W2167847032","https://openalex.org/W2168440643","https://openalex.org/W2169024178","https://openalex.org/W2169387919","https://openalex.org/W2170037597","https://openalex.org/W2170478076","https://openalex.org/W2171574281","https://openalex.org/W2173213060","https://openalex.org/W2182703380","https://openalex.org/W2184381445","https://openalex.org/W2208310611","https://openalex.org/W2210065635","https://openalex.org/W2216499221","https://openalex.org/W2239873446","https://openalex.org/W2243458913","https://openalex.org/W2250539671","https://openalex.org/W2270436279","https://openalex.org/W2286724461","https://openalex.org/W2289049650","https://openalex.org/W2293638404","https://openalex.org/W2294331997","https://openalex.org/W2318063279","https://openalex.org/W2396588571","https://openalex.org/W2397525010","https://openalex.org/W2397994241","https://openalex.org/W2398333000","https://openalex.org/W2399361902","https://openalex.org/W2424113438","https://openalex.org/W2430378630","https://openalex.org/W2441805796","https://openalex.org/W2492590231","https://openalex.org/W2516893773","https://openalex.org/W2518732252","https://openalex.org/W2529367823","https://openalex.org/W2535168187","https://openalex.org/W2542998387","https://openalex.org/W2551739211","https://openalex.org/W2559870814","https://openalex.org/W2562696781","https://openalex.org/W2574633002","https://openalex.org/W2585236354","https://openalex.org/W2597556072","https://openalex.org/W2606791715","https://openalex.org/W2607666848","https://openalex.org/W2612288690","https://openalex.org/W2613666425","https://openalex.org/W2615445186","https://openalex.org/W2615658008","https://openalex.org/W2615785180","https://openalex.org/W2616120155","https://openalex.org/W2619410666","https://openalex.org/W2724295488","https://openalex.org/W2750964846","https://openalex.org/W2751539668","https://openalex.org/W2752274179","https://openalex.org/W2766530067","https://openalex.org/W2771365767","https://openalex.org/W2789873654","https://openalex.org/W2790957175","https://openalex.org/W2792196230","https://openalex.org/W2794107983","https://openalex.org/W2795151173","https://openalex.org/W2795518213","https://openalex.org/W2804222599","https://openalex.org/W2808963673","https://openalex.org/W2883952940","https://openalex.org/W2886192825","https://openalex.org/W2889353337","https://openalex.org/W2893314940","https://openalex.org/W2903296288","https://openalex.org/W2904953191","https://openalex.org/W2905135414","https://openalex.org/W2911280950","https://openalex.org/W2912306800","https://openalex.org/W2923968079","https://openalex.org/W2925054201","https://openalex.org/W2930957955","https://openalex.org/W2946741276","https://openalex.org/W2948163032","https://openalex.org/W2951438725","https://openalex.org/W2954727071","https://openalex.org/W2957204582","https://openalex.org/W2963784432","https://openalex.org/W2963886823","https://openalex.org/W2967709572","https://openalex.org/W2971101812","https://openalex.org/W3011807731","https://openalex.org/W3102192406","https://openalex.org/W3146259567","https://openalex.org/W4210956590","https://openalex.org/W4299626704","https://openalex.org/W4300456194","https://openalex.org/W4372267129","https://openalex.org/W6684974537","https://openalex.org/W6685831320","https://openalex.org/W6729714802","https://openalex.org/W6735423003"],"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/W2017131087"],"abstract_inverted_index":{"Entity":[0],"Resolution":[1],"(ER),":[2],"a":[3,26,44,102],"core":[4],"task":[5],"of":[6,28,47,105],"Data":[7],"Integration,":[8],"detects":[9],"different":[10,52,95],"entity":[11,64,77],"profiles":[12],"that":[13,33,66,79,93],"correspond":[14],"to":[15,21,36,63,70,82],"the":[16,73,106,112,118,126],"same":[17],"real-world":[18],"object.":[19],"Due":[20],"its":[22],"inherently":[23],"quadratic":[24],"complexity,":[25],"series":[27],"techniques":[29],"accelerate":[30],"it":[31,34],"so":[32],"scales":[35],"voluminous":[37],"data.":[38],"In":[39],"this":[40],"survey,":[41],"we":[42,100],"review":[43],"large":[45],"number":[46],"relevant":[48,107],"works":[49],"under":[50],"two":[51],"but":[53],"related":[54],"frameworks:":[55],"Blocking":[56],"and":[57],"Filtering.":[58],"The":[59],"former":[60],"restricts":[61],"comparisons":[62],"pairs":[65,78],"are":[67,80],"more":[68],"likely":[69,81],"match,":[71],"while":[72],"latter":[74],"identifies":[75],"quickly":[76],"satisfy":[83],"predetermined":[84],"similarity":[85],"thresholds.":[86],"We":[87,115],"also":[88],"elaborate":[89],"on":[90],"hybrid":[91],"approaches":[92],"combine":[94],"characteristics.":[96],"For":[97],"each":[98],"framework":[99],"provide":[101],"comprehensive":[103],"list":[104],"works,":[108],"discussing":[109],"them":[110],"in":[111,125],"greater":[113],"context.":[114],"conclude":[116],"with":[117],"most":[119],"promising":[120],"directions":[121],"for":[122],"future":[123],"work":[124],"field.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":19},{"year":2025,"cited_by_count":40},{"year":2024,"cited_by_count":29},{"year":2023,"cited_by_count":44},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":30},{"year":2020,"cited_by_count":10},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2020-04-10T00:00:00"}