{"id":"https://openalex.org/W2210065635","doi":"https://doi.org/10.14778/2856318.2856326","title":"Schema-agnostic vs schema-based configurations for blocking methods on homogeneous data","display_name":"Schema-agnostic vs schema-based configurations for blocking methods on homogeneous data","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2210065635","doi":"https://doi.org/10.14778/2856318.2856326","mag":"2210065635"},"language":"en","primary_location":{"id":"doi:10.14778/2856318.2856326","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2856318.2856326","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":false,"raw_author_name":"George Papadakis","raw_affiliation_strings":["University of Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Athens, Greece","institution_ids":["https://openalex.org/I200777214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053637778","display_name":"George Alexiou","orcid":"https://orcid.org/0000-0003-2244-4916"},"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":"George Alexiou","raw_affiliation_strings":["IMIS, Research Center \"Athena\", Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IMIS, Research Center \"Athena\", Greece","institution_ids":["https://openalex.org/I4210156054"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001091619","display_name":"George Papastefanatos","orcid":"https://orcid.org/0000-0002-9273-9843"},"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":"George Papastefanatos","raw_affiliation_strings":["IMIS, Research Center \"Athena\", Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IMIS, Research Center \"Athena\", Greece","institution_ids":["https://openalex.org/I4210156054"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012623045","display_name":"Georgia Koutrika","orcid":"https://orcid.org/0000-0002-7377-0116"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Georgia Koutrika","raw_affiliation_strings":["HP Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Labs","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.2139,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.96978503,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"9","issue":"4","first_page":"312","last_page":"323"},"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":0.9739000201225281,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9394999742507935,"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":0.7657971382141113},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.7204070687294006},{"id":"https://openalex.org/keywords/optimal-distinctiveness-theory","display_name":"Optimal distinctiveness theory","score":0.4958079755306244},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4697559177875519},{"id":"https://openalex.org/keywords/star-schema","display_name":"Star schema","score":0.4594268798828125},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.45378774404525757},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37596508860588074},{"id":"https://openalex.org/keywords/database-schema","display_name":"Database schema","score":0.371782124042511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3219263553619385},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3111533224582672},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1361657977104187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7657971382141113},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.7204070687294006},{"id":"https://openalex.org/C47385372","wikidata":"https://www.wikidata.org/wiki/Q7098943","display_name":"Optimal distinctiveness theory","level":2,"score":0.4958079755306244},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4697559177875519},{"id":"https://openalex.org/C190703929","wikidata":"https://www.wikidata.org/wiki/Q1331138","display_name":"Star schema","level":4,"score":0.4594268798828125},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.45378774404525757},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37596508860588074},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.371782124042511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3219263553619385},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3111533224582672},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1361657977104187},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2856318.2856326","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2856318.2856326","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W26430610","https://openalex.org/W192652968","https://openalex.org/W343945789","https://openalex.org/W1540269031","https://openalex.org/W1588213250","https://openalex.org/W1997927541","https://openalex.org/W2007682403","https://openalex.org/W2024770506","https://openalex.org/W2031250218","https://openalex.org/W2036216970","https://openalex.org/W2041439319","https://openalex.org/W2065398649","https://openalex.org/W2073471108","https://openalex.org/W2077044633","https://openalex.org/W2079649893","https://openalex.org/W2108991785","https://openalex.org/W2111116800","https://openalex.org/W2112912553","https://openalex.org/W2117974736","https://openalex.org/W2128661986","https://openalex.org/W2152502401","https://openalex.org/W2158418361","https://openalex.org/W2161936973","https://openalex.org/W2166400748","https://openalex.org/W2171574281","https://openalex.org/W2318063279","https://openalex.org/W2397994241","https://openalex.org/W2529367823","https://openalex.org/W6632038546","https://openalex.org/W6676669657","https://openalex.org/W6683401941","https://openalex.org/W6700160807","https://openalex.org/W6824611359"],"related_works":["https://openalex.org/W2034415381","https://openalex.org/W2087376388","https://openalex.org/W2103472145","https://openalex.org/W2092058806","https://openalex.org/W2042840812","https://openalex.org/W1561927997","https://openalex.org/W1992271858","https://openalex.org/W160336554","https://openalex.org/W2389917040","https://openalex.org/W166845585"],"abstract_inverted_index":{"Entity":[0],"Resolution":[1],"constitutes":[2],"a":[3,60,148,170,175],"core":[4],"task":[5],"for":[6,174],"data":[7],"integration":[8],"that,":[9],"due":[10],"to":[11,17,39,79,94,120,126],"its":[12,89],"quadratic":[13],"complexity,":[14],"typically":[15],"scales":[16],"large":[18],"datasets":[19],"through":[20],"blocking":[21,123,142,164,190],"methods.":[22],"These":[23],"can":[24],"be":[25],"configured":[26],"in":[27,37,109],"two":[28,107],"ways.":[29],"The":[30,62],"schema-based":[31,96,181],"configuration":[32,157],"relies":[33],"on":[34,88],"schema":[35,193],"information":[36],"order":[38],"select":[40],"signatures":[41],"of":[42,111,129,140,147,163,188],"high":[43],"distinctiveness":[44],"and":[45,76,115,125,160],"low":[46],"noise,":[47],"while":[48],"the":[49,95,106,137,141,145,155,180,186],"schema-agnostic":[50,156],"one":[51],"treats":[52],"every":[53],"token":[54],"from":[55],"all":[56],"attribute":[57],"values":[58],"as":[59,68],"signature.":[61],"latter":[63],"approach":[64],"has":[65],"significant":[66],"potential,":[67],"it":[69,77],"requires":[70],"no":[71,85],"fine-tuning":[72],"by":[73,103],"human":[74],"experts":[75],"applies":[78],"heterogeneous":[80],"data.":[81,131],"Yet,":[82],"there":[83],"is":[84],"systematic":[86],"study":[87],"relative":[90],"performance":[91],"with":[92,144],"respect":[93],"configuration.":[97],"This":[98],"work":[99],"covers":[100],"this":[101],"gap":[102],"comparing":[104],"analytically":[105],"configurations":[108],"terms":[110],"effectiveness,":[112],"time":[113],"efficiency":[114],"scalability.":[116],"We":[117,132],"apply":[118],"them":[119],"9":[121],"established":[122],"methods":[124,143,191],"11":[127],"benchmarks":[128],"structured":[130],"provide":[133],"valuable":[134],"insights":[135],"into":[136],"internal":[138],"functionality":[139],"help":[146],"novel":[149],"taxonomy.":[150],"Our":[151],"studies":[152],"reveal":[153],"that":[154],"offers":[158],"unsupervised":[159],"robust":[161],"definition":[162],"keys":[165],"under":[166],"versatile":[167],"settings,":[168],"trading":[169],"higher":[171,177],"computational":[172],"cost":[173],"consistently":[176],"recall":[178],"than":[179],"one.":[182],"It":[183],"also":[184],"enables":[185],"use":[187],"state-of-the-art":[189],"without":[192],"knowledge.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}