{"id":"https://openalex.org/W3092962901","doi":"https://doi.org/10.1145/3418896","title":"An Overview of End-to-End Entity Resolution for Big Data","display_name":"An Overview of End-to-End Entity Resolution for Big Data","publication_year":2020,"publication_date":"2020-12-06","ids":{"openalex":"https://openalex.org/W3092962901","doi":"https://doi.org/10.1145/3418896","mag":"3092962901"},"language":"en","primary_location":{"id":"doi:10.1145/3418896","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3418896","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042003138","display_name":"Vassilis Christophides","orcid":"https://orcid.org/0000-0002-2076-1881"},"institutions":[{"id":"https://openalex.org/I86175216","display_name":"\u00c9cole Nationale Sup\u00e9rieure de l'\u00c9lectronique et de ses Applications","ror":"https://ror.org/03qeacd72","country_code":"FR","type":"education","lineage":["https://openalex.org/I86175216"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Vassilis Christophides","raw_affiliation_strings":["ENSEA, ETIS Lab, Cergy France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ENSEA, ETIS Lab, Cergy France","institution_ids":["https://openalex.org/I86175216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073440687","display_name":"Vasilis Efthymiou","orcid":"https://orcid.org/0000-0002-0683-030X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vasilis Efthymiou","raw_affiliation_strings":["IBM Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053726723","display_name":"Themis Palpanas","orcid":"https://orcid.org/0000-0002-8031-0265"},"institutions":[{"id":"https://openalex.org/I121303486","display_name":"University of London Institute in Paris","ror":"https://ror.org/045svrn73","country_code":"FR","type":"education","lineage":["https://openalex.org/I121303486","https://openalex.org/I124357947"]},{"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":["Universit\u00e9 de Paris and French University Institute (IUF), Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Paris and French University Institute (IUF), Paris, France","institution_ids":["https://openalex.org/I121303486","https://openalex.org/I204730241"]}]},{"author_position":"middle","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":["National and Kapodistrian University of Athens, Panepistimioupolis, Ilissia, Athens, Greece"],"raw_orcid":"https://orcid.org/0000-0002-7298-9431","affiliations":[{"raw_affiliation_string":"National and Kapodistrian University of Athens, Panepistimioupolis, Ilissia, Athens, Greece","institution_ids":["https://openalex.org/I200777214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042740371","display_name":"Kostas Stefanidis","orcid":"https://orcid.org/0000-0003-1317-8062"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Kostas Stefanidis","raw_affiliation_strings":["Tampere University, Kalevantie, Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University, Kalevantie, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":20.2486,"has_fulltext":false,"cited_by_count":228,"citation_normalized_percentile":{"value":0.99658997,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"53","issue":"6","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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9842000007629395,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9069969654083252},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7479105591773987},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7229118943214417},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6782462000846863},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6674826145172119},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5398845076560974},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4628630578517914},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.438959002494812},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3287924528121948},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2758845090866089},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.27441173791885376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2559376358985901}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9069969654083252},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7479105591773987},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7229118943214417},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6782462000846863},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6674826145172119},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5398845076560974},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4628630578517914},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.438959002494812},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3287924528121948},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2758845090866089},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27441173791885376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2559376358985901},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3418896","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3418896","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:HAL:hal-04319720v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04319720","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM Computing Surveys, 2020, 53 (6), pp.1-42. ⟨10.1145/3418896⟩","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:trepo.tuni.fi:10024/217849","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/217849","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","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":"reviewarticle"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G4189288737","display_name":null,"funder_award_id":"825258","funder_id":"https://openalex.org/F4320335254","funder_display_name":"Horizon 2020"}],"funders":[{"id":"https://openalex.org/F4320335254","display_name":"Horizon 2020","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":172,"referenced_works":["https://openalex.org/W66673523","https://openalex.org/W69311973","https://openalex.org/W87992039","https://openalex.org/W192652968","https://openalex.org/W192724328","https://openalex.org/W299839057","https://openalex.org/W1124123724","https://openalex.org/W1496255159","https://openalex.org/W1504263697","https://openalex.org/W1519440323","https://openalex.org/W1524281572","https://openalex.org/W1559390933","https://openalex.org/W1597082186","https://openalex.org/W1602412127","https://openalex.org/W1964786778","https://openalex.org/W1975167882","https://openalex.org/W1975184797","https://openalex.org/W1976437052","https://openalex.org/W1982287794","https://openalex.org/W1982350890","https://openalex.org/W1992419399","https://openalex.org/W1995099886","https://openalex.org/W1995541812","https://openalex.org/W1997927541","https://openalex.org/W2007682403","https://openalex.org/W2014964486","https://openalex.org/W2016589492","https://openalex.org/W2016973429","https://openalex.org/W2017167478","https://openalex.org/W2019150658","https://openalex.org/W2024386211","https://openalex.org/W2030433745","https://openalex.org/W2030724586","https://openalex.org/W2031250218","https://openalex.org/W2032382962","https://openalex.org/W2040240412","https://openalex.org/W2041439319","https://openalex.org/W2046020929","https://openalex.org/W2047940964","https://openalex.org/W2053653724","https://openalex.org/W2056748234","https://openalex.org/W2064244056","https://openalex.org/W2073471108","https://openalex.org/W2081118310","https://openalex.org/W2089965140","https://openalex.org/W2102350406","https://openalex.org/W2103561765","https://openalex.org/W2103734666","https://openalex.org/W2104511295","https://openalex.org/W2106675345","https://openalex.org/W2107499437","https://openalex.org/W2107799451","https://openalex.org/W2107966677","https://openalex.org/W2108087318","https://openalex.org/W2110485445","https://openalex.org/W2114432090","https://openalex.org/W2114538147","https://openalex.org/W2114764731","https://openalex.org/W2115219423","https://openalex.org/W2122865749","https://openalex.org/W2123561513","https://openalex.org/W2129607105","https://openalex.org/W2132658991","https://openalex.org/W2139021951","https://openalex.org/W2139490252","https://openalex.org/W2140789797","https://openalex.org/W2147299132","https://openalex.org/W2148019918","https://openalex.org/W2148524305","https://openalex.org/W2152502401","https://openalex.org/W2154756203","https://openalex.org/W2158418361","https://openalex.org/W2163051926","https://openalex.org/W2164456230","https://openalex.org/W2168440643","https://openalex.org/W2169024178","https://openalex.org/W2169940602","https://openalex.org/W2171450492","https://openalex.org/W2173213060","https://openalex.org/W2208310611","https://openalex.org/W2210065635","https://openalex.org/W2220488081","https://openalex.org/W2237063244","https://openalex.org/W2239873446","https://openalex.org/W2243458913","https://openalex.org/W2256424113","https://openalex.org/W2261544779","https://openalex.org/W2271987422","https://openalex.org/W2295256067","https://openalex.org/W2295925036","https://openalex.org/W2318063279","https://openalex.org/W2323506184","https://openalex.org/W2399361902","https://openalex.org/W2399456070","https://openalex.org/W2407445562","https://openalex.org/W2428834396","https://openalex.org/W2492590231","https://openalex.org/W2507358938","https://openalex.org/W2535168187","https://openalex.org/W2546466160","https://openalex.org/W2551361256","https://openalex.org/W2559870814","https://openalex.org/W2584608588","https://openalex.org/W2604869579","https://openalex.org/W2612925715","https://openalex.org/W2612964472","https://openalex.org/W2613666425","https://openalex.org/W2615445186","https://openalex.org/W2733471169","https://openalex.org/W2741750617","https://openalex.org/W2748156246","https://openalex.org/W2751539668","https://openalex.org/W2753000574","https://openalex.org/W2762307198","https://openalex.org/W2765590357","https://openalex.org/W2769041395","https://openalex.org/W2771365767","https://openalex.org/W2794107983","https://openalex.org/W2795151173","https://openalex.org/W2798396018","https://openalex.org/W2798649495","https://openalex.org/W2799106927","https://openalex.org/W2805602976","https://openalex.org/W2808345493","https://openalex.org/W2811097925","https://openalex.org/W2884061367","https://openalex.org/W2885947181","https://openalex.org/W2889066742","https://openalex.org/W2889284307","https://openalex.org/W2890187992","https://openalex.org/W2893314940","https://openalex.org/W2896766043","https://openalex.org/W2898851569","https://openalex.org/W2900130171","https://openalex.org/W2903963001","https://openalex.org/W2914959486","https://openalex.org/W2918032799","https://openalex.org/W2923968079","https://openalex.org/W2925054201","https://openalex.org/W2925156238","https://openalex.org/W2927570825","https://openalex.org/W2929962453","https://openalex.org/W2933781133","https://openalex.org/W2946504770","https://openalex.org/W2951147191","https://openalex.org/W2952068610","https://openalex.org/W2957204582","https://openalex.org/W2959716049","https://openalex.org/W2962916648","https://openalex.org/W2962936818","https://openalex.org/W2964855489","https://openalex.org/W2966720878","https://openalex.org/W2992897306","https://openalex.org/W2998655947","https://openalex.org/W2998704965","https://openalex.org/W3011807731","https://openalex.org/W3014689699","https://openalex.org/W3045341009","https://openalex.org/W3099734810","https://openalex.org/W3099883947","https://openalex.org/W4210956590","https://openalex.org/W4233366162","https://openalex.org/W4242744113","https://openalex.org/W4246553962","https://openalex.org/W4249572517","https://openalex.org/W4299626704","https://openalex.org/W4300456194","https://openalex.org/W4302802341","https://openalex.org/W4372267129","https://openalex.org/W6684974537","https://openalex.org/W6693078765","https://openalex.org/W6753098016"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W4394895745","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W3023919550","https://openalex.org/W2019038080"],"abstract_inverted_index":{"One":[0],"of":[1,14,37,52,64,115,127,139],"the":[2,12,30,49,65,78,103,135,145],"most":[3],"critical":[4],"tasks":[5],"for":[6,130],"improving":[7],"data":[8,15],"quality":[9],"and":[10,72,83,94,112,137,142],"increasing":[11],"reliability":[13],"analytics":[16],"is":[17],"Entity":[18],"Resolution":[19],"(ER),":[20],"which":[21],"aims":[22],"to":[23,29,100],"identify":[24],"different":[25],"descriptions":[26,117],"that":[27,86],"refer":[28],"same":[31],"real-world":[32,120],"entity.":[33],"Despite":[34],"several":[35],"decades":[36],"research,":[38],"ER":[39,128],"remains":[40],"a":[41],"challenging":[42],"problem.":[43],"In":[44],"this":[45],"survey,":[46],"we":[47,58],"highlight":[48],"novel":[50],"aspects":[51],"resolving":[53],"Big":[54,66,131],"Data":[55,67],"entities":[56],"when":[57],"should":[59],"satisfy":[60],"more":[61],"than":[62],"one":[63],"characteristics":[68],"simultaneously":[69],"(i.e.,":[70],"Volume":[71],"Velocity":[73],"with":[74,102,144],"Variety).":[75],"We":[76,122],"present":[77],"basic":[79],"concepts,":[80],"processing":[81],"steps,":[82],"execution":[84],"strategies":[85],"have":[87],"been":[88],"proposed":[89],"by":[90,119],"database,":[91],"semantic":[92],"Web,":[93],"machine":[95],"learning":[96],"communities":[97],"in":[98],"order":[99],"cope":[101],"loose":[104],"structuredness":[105],",":[106,109],"extreme":[107],"diversity":[108],"high":[110],"speed,":[111],"large":[113],"scale":[114],"entity":[116],"used":[118],"applications.":[121],"provide":[123],"an":[124],"end-to-end":[125],"view":[126],"workflows":[129],"Data,":[132],"critically":[133],"review":[134],"pros":[136],"cons":[138],"existing":[140],"methods,":[141],"conclude":[143],"main":[146],"open":[147],"research":[148],"directions.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":22},{"year":2025,"cited_by_count":41},{"year":2024,"cited_by_count":40},{"year":2023,"cited_by_count":63},{"year":2022,"cited_by_count":28},{"year":2021,"cited_by_count":33},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}