{"id":"https://openalex.org/W2946741276","doi":"https://doi.org/10.1109/tkde.2018.2852763","title":"Schema-Agnostic Progressive Entity Resolution","display_name":"Schema-Agnostic Progressive Entity Resolution","publication_year":2018,"publication_date":"2018-07-04","ids":{"openalex":"https://openalex.org/W2946741276","doi":"https://doi.org/10.1109/tkde.2018.2852763","mag":"2946741276"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2018.2852763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2018.2852763","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.06385","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047630333","display_name":"Giovanni Simonini","orcid":"https://orcid.org/0000-0002-3466-509X"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]},{"id":"https://openalex.org/I4210161797","display_name":"Ferrari (Italy)","ror":"https://ror.org/05p859a12","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210161797"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Simonini","raw_affiliation_strings":["Department of Engineering, \u201cEnzo Ferrari\u201d of the University of Modena and Reggio Emilia, Modena, MO, Italy","Department of Engineering, \"Enzo Ferrari\" of the University of Modena and Reggio Emilia, Modena, MO, Italy"],"raw_orcid":"https://orcid.org/0000-0002-3466-509X","affiliations":[{"raw_affiliation_string":"Department of Engineering, \u201cEnzo Ferrari\u201d of the University of Modena and Reggio Emilia, Modena, MO, Italy","institution_ids":["https://openalex.org/I122346577"]},{"raw_affiliation_string":"Department of Engineering, \"Enzo Ferrari\" of the University of Modena and Reggio Emilia, Modena, MO, Italy","institution_ids":["https://openalex.org/I122346577","https://openalex.org/I4210161797"]}]},{"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":["University of Athens, Athens, Greece"],"raw_orcid":"https://orcid.org/0000-0002-7298-9431","affiliations":[{"raw_affiliation_string":"University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I200777214"]}]},{"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/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, Paris, France"],"raw_orcid":"https://orcid.org/0000-0002-8031-0265","affiliations":[{"raw_affiliation_string":"Paris Descartes University, Paris, France","institution_ids":["https://openalex.org/I110736937","https://openalex.org/I204730241"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037830808","display_name":"Sonia Bergamaschi","orcid":"https://orcid.org/0000-0001-8087-6587"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]},{"id":"https://openalex.org/I4210161797","display_name":"Ferrari (Italy)","ror":"https://ror.org/05p859a12","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210161797"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sonia Bergamaschi","raw_affiliation_strings":["Department of Engineering, \u201cEnzo Ferrari\u201d of the University of Modena and Reggio Emilia, Modena, MO, Italy","Department of Engineering, \"Enzo Ferrari\" of the University of Modena and Reggio Emilia, Modena, MO, Italy"],"raw_orcid":"https://orcid.org/0000-0001-8087-6587","affiliations":[{"raw_affiliation_string":"Department of Engineering, \u201cEnzo Ferrari\u201d of the University of Modena and Reggio Emilia, Modena, MO, Italy","institution_ids":["https://openalex.org/I122346577"]},{"raw_affiliation_string":"Department of Engineering, \"Enzo Ferrari\" of the University of Modena and Reggio Emilia, Modena, MO, Italy","institution_ids":["https://openalex.org/I122346577","https://openalex.org/I4210161797"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1349,"has_fulltext":true,"cited_by_count":63,"citation_normalized_percentile":{"value":0.95605586,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"31","issue":"6","first_page":"1208","last_page":"1221"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9957000017166138,"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":0.9861000180244446,"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":0.8755416870117188},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.6694013476371765},{"id":"https://openalex.org/keywords/schema-migration","display_name":"Schema migration","score":0.5082821249961853},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48463350534439087},{"id":"https://openalex.org/keywords/database-schema","display_name":"Database schema","score":0.46822282671928406},{"id":"https://openalex.org/keywords/star-schema","display_name":"Star schema","score":0.4631113111972809},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4443241059780121},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.43717247247695923},{"id":"https://openalex.org/keywords/information-schema","display_name":"Information schema","score":0.43187010288238525},{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.4281129240989685},{"id":"https://openalex.org/keywords/conceptual-schema","display_name":"Conceptual schema","score":0.4145946800708771},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.3816101849079132},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3195376396179199},{"id":"https://openalex.org/keywords/semi-structured-model","display_name":"Semi-structured model","score":0.29418864846229553},{"id":"https://openalex.org/keywords/database-design","display_name":"Database design","score":0.11217519640922546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8755416870117188},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6694013476371765},{"id":"https://openalex.org/C153440673","wikidata":"https://www.wikidata.org/wiki/Q7431119","display_name":"Schema migration","level":5,"score":0.5082821249961853},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48463350534439087},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.46822282671928406},{"id":"https://openalex.org/C190703929","wikidata":"https://www.wikidata.org/wiki/Q1331138","display_name":"Star schema","level":4,"score":0.4631113111972809},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4443241059780121},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.43717247247695923},{"id":"https://openalex.org/C150012506","wikidata":"https://www.wikidata.org/wiki/Q6031185","display_name":"Information schema","level":5,"score":0.43187010288238525},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.4281129240989685},{"id":"https://openalex.org/C29275276","wikidata":"https://www.wikidata.org/wiki/Q2268965","display_name":"Conceptual schema","level":3,"score":0.4145946800708771},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.3816101849079132},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3195376396179199},{"id":"https://openalex.org/C56310702","wikidata":"https://www.wikidata.org/wiki/Q2269281","display_name":"Semi-structured model","level":4,"score":0.29418864846229553},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.11217519640922546},{"id":"https://openalex.org/C165611974","wikidata":"https://www.wikidata.org/wiki/Q5531015","display_name":"Gender schema theory","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tkde.2018.2852763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2018.2852763","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:arXiv.org:1905.06385","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.06385","pdf_url":"https://arxiv.org/pdf/1905.06385","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:iris.unimore.it:11380/1191056","is_oa":true,"landing_page_url":"http://hdl.handle.net/11380/1191056","pdf_url":"https://iris.unimore.it/bitstream/11380/1191056/2/saper_TKDE.pdf","source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.06385","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.06385","pdf_url":"https://arxiv.org/pdf/1905.06385","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"display_name":"No poverty","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1504263697","https://openalex.org/W1540269031","https://openalex.org/W1599547597","https://openalex.org/W1981590391","https://openalex.org/W1982350890","https://openalex.org/W1992930793","https://openalex.org/W1994229028","https://openalex.org/W2013093146","https://openalex.org/W2024770506","https://openalex.org/W2031250218","https://openalex.org/W2041439319","https://openalex.org/W2056748234","https://openalex.org/W2065758089","https://openalex.org/W2101654853","https://openalex.org/W2106675345","https://openalex.org/W2108087318","https://openalex.org/W2123561513","https://openalex.org/W2128661986","https://openalex.org/W2145908616","https://openalex.org/W2156543375","https://openalex.org/W2163051926","https://openalex.org/W2168440643","https://openalex.org/W2210065635","https://openalex.org/W2237063244","https://openalex.org/W2243458913","https://openalex.org/W2270436279","https://openalex.org/W2398333000","https://openalex.org/W2516893773","https://openalex.org/W2535168187","https://openalex.org/W2559870814","https://openalex.org/W2613666425","https://openalex.org/W2615445186","https://openalex.org/W2950833813","https://openalex.org/W2951938755","https://openalex.org/W3030552871","https://openalex.org/W4210956590","https://openalex.org/W4254788633","https://openalex.org/W4285719527","https://openalex.org/W4300456194","https://openalex.org/W4300601563","https://openalex.org/W6632038546","https://openalex.org/W6635624157","https://openalex.org/W6712710463"],"related_works":["https://openalex.org/W945629821","https://openalex.org/W2584207435","https://openalex.org/W1499427961","https://openalex.org/W2766698234","https://openalex.org/W172068681","https://openalex.org/W2131981997","https://openalex.org/W2373484664","https://openalex.org/W1971380397","https://openalex.org/W2964271791","https://openalex.org/W896179304"],"abstract_inverted_index":{"Entity":[0],"Resolution":[1],"(ER)":[2],"is":[3,37],"the":[4,13,40,47,52,64,72,92,102,210,219,222,229,233,239],"task":[5],"of":[6,51,66,94,143,160,187,232],"finding":[7],"entity":[8,53,103],"profiles":[9],"that":[10,100,172,179,208],"correspond":[11],"to":[12,20,38,79,88,156,184,214],"same":[14],"real-world":[15],"entity.":[16],"Progressive":[17,57,145],"ER":[18,58,146],"aims":[19],"efficiently":[21],"resolve":[22],"large":[23,120,185],"datasets":[24],"when":[25],"limited":[26],"time":[27],"and/or":[28],"computational":[29],"resources":[30],"are":[31,110],"available.":[32],"In":[33],"practice,":[34],"its":[35],"goal":[36],"provide":[39],"best":[41],"possible":[42],"partial":[43],"solution":[44],"by":[45],"approximating":[46],"optimal":[48],"comparison":[49],"order":[50],"profiles.":[54],"So":[55],"far,":[56],"has":[59],"only":[60],"been":[61],"examined":[62],"in":[63,113],"context":[65],"structured":[67],"(relational)":[68],"data":[69,158],"sources,":[70],"as":[71,125],"existing":[73],"methods":[74,212],"rely":[75],"on":[76,238],"schema":[77,152,162],"knowledge":[78],"save":[80],"unnecessary":[81],"comparisons:":[82],"they":[83],"restrict":[84],"their":[85],"search":[86],"space":[87],"similar":[89],"entities":[90],"with":[91],"help":[93],"schema-based":[95,224],"blocking":[96],"keys":[97],"(i.e.,":[98],"signatures":[99],"represent":[101],"profiles).":[104],"As":[105],"a":[106,141,176,215],"result,":[107],"these":[108],"solutions":[109,174],"not":[111,150,181],"applicable":[112],"Big":[114],"Data":[115],"integration":[116],"applications,":[117],"which":[118,148],"involve":[119],"and":[121,127,221],"heterogeneous":[122,157],"datasets,":[123,205],"such":[124],"relational":[126],"RDF":[128],"databases,":[129],"JSON":[130],"files,":[131],"Web":[132],"corpus":[133],"etc.":[134],"To":[135],"cover":[136],"this":[137],"gap,":[138],"we":[139,165,190,206],"propose":[140,191],"family":[142],"schema-agnostic":[144,169],"methods,":[147,170,235],"do":[149],"require":[151],"information,":[153],"thus":[154],"applying":[155],"sources":[159],"any":[161],"variety.":[163],"First,":[164],"introduce":[166],"two":[167],"na\u00efve":[168,220],"showing":[171],"straightforward":[173],"exhibit":[175],"poor":[177],"performance":[178,231],"does":[180],"scale":[182],"well":[183],"volumes":[186],"data.":[188],"Then,":[189],"four":[192],"different":[193],"advanced":[194,211,234],"methods.":[195],"Through":[196],"an":[197],"extensive":[198],"experimental":[199],"evaluation":[200],"over":[201],"7":[202],"real-world,":[203],"established":[204],"show":[207],"all":[209],"outperform":[213],"significant":[216],"extent":[217],"both":[218],"state-of-the-art":[223],"ones.":[225],"We":[226],"also":[227],"investigate":[228],"relative":[230],"providing":[236],"guidelines":[237],"method":[240],"selection.":[241]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2019-05-29T00:00:00"}
