{"id":"https://openalex.org/W2163616098","doi":"https://doi.org/10.1145/1999299.1999302","title":"To compare or not to compare","display_name":"To compare or not to compare","publication_year":2011,"publication_date":"2011-06-12","ids":{"openalex":"https://openalex.org/W2163616098","doi":"https://doi.org/10.1145/1999299.1999302","mag":"2163616098"},"language":"en","primary_location":{"id":"doi:10.1145/1999299.1999302","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1999299.1999302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on Semantic Web Information Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://doi.org/10.1145/1999299.1999302","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/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]},{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE","GR"],"is_corresponding":false,"raw_author_name":"George Papadakis","raw_affiliation_strings":["National Technical University of Athens, Greece and L3S Research Center, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Technical University of Athens, Greece and L3S Research Center, Germany","institution_ids":["https://openalex.org/I174458059","https://openalex.org/I4210136150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084886581","display_name":"Ekaterini Ioannou","orcid":"https://orcid.org/0000-0002-4922-6639"},"institutions":[{"id":"https://openalex.org/I55741626","display_name":"Technical University of Crete","ror":"https://ror.org/03f8bz564","country_code":"GR","type":"education","lineage":["https://openalex.org/I55741626"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Ekaterini Ioannou","raw_affiliation_strings":["Technical University of Crete, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Crete, Greece","institution_ids":["https://openalex.org/I55741626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037478463","display_name":"Claudia Nieder\u00e9e","orcid":"https://orcid.org/0000-0002-2959-0484"},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Claudia Nieder\u00e9e","raw_affiliation_strings":["L3S Research Center, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Center, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"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/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Themis Palpanas","raw_affiliation_strings":["University of Trento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074427964","display_name":"Wolfgang Nejdl","orcid":"https://orcid.org/0000-0003-3374-2193"},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfgang Nejdl","raw_affiliation_strings":["L3S Research Center, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Center, Germany","institution_ids":["https://openalex.org/I4210136150"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.9921000003814697,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.980400025844574,"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":0.813133955001831},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.6315945386886597},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5929697751998901},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5779399871826172},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.5469754338264465},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5385509729385376},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5267733335494995},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.512117862701416},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3270336985588074},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28683537244796753},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.15960192680358887}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.813133955001831},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.6315945386886597},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5929697751998901},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5779399871826172},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.5469754338264465},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5385509729385376},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5267733335494995},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.512117862701416},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3270336985588074},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28683537244796753},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.15960192680358887},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1999299.1999302","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1999299.1999302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on Semantic Web Information Management","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.lib.ntua.gr:123456789/36371","is_oa":true,"landing_page_url":"http://doi.org/10.1145/1999299.1999302","pdf_url":null,"source":{"id":"https://openalex.org/S4377196837","display_name":"DSpace - NTUA (National Technical University of Athens)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I174458059","host_organization_name":"National Technical University of Athens","host_organization_lineage":["https://openalex.org/I174458059"],"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":"Proceedings of the International Workshop on Semantic Web Information Management, SWIM 2011","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:iris.unitn.it:11572/88860","is_oa":false,"landing_page_url":"http://hdl.handle.net/11572/88860","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:dspace.lib.ntua.gr:123456789/36371","is_oa":true,"landing_page_url":"http://doi.org/10.1145/1999299.1999302","pdf_url":null,"source":{"id":"https://openalex.org/S4377196837","display_name":"DSpace - NTUA (National Technical University of Athens)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I174458059","host_organization_name":"National Technical University of Athens","host_organization_lineage":["https://openalex.org/I174458059"],"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":"Proceedings of the International Workshop on Semantic Web Information Management, SWIM 2011","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1540269031","https://openalex.org/W1967208734","https://openalex.org/W1992930793","https://openalex.org/W2024770506","https://openalex.org/W2036216970","https://openalex.org/W2073539176","https://openalex.org/W2088008685","https://openalex.org/W2108991785","https://openalex.org/W2109834209","https://openalex.org/W2111116800","https://openalex.org/W2117974736","https://openalex.org/W2161936973","https://openalex.org/W6632038546","https://openalex.org/W6683401941"],"related_works":["https://openalex.org/W2471940468","https://openalex.org/W2392835431","https://openalex.org/W4226075635","https://openalex.org/W2126932387","https://openalex.org/W1965371215","https://openalex.org/W1528218860","https://openalex.org/W2406112091","https://openalex.org/W2125859764","https://openalex.org/W2029826694","https://openalex.org/W2159303222"],"abstract_inverted_index":{"Blocking":[0],"methods":[1,17],"are":[2,37,144],"crucial":[3],"for":[4,140,157],"making":[5],"the":[6,20,24,29,40,48,68,83,87,111,159,175],"inherently":[7],"quadratic":[8],"task":[9],"of":[10,26,31,47,89,104,115,177],"Entity":[11],"Resolution":[12],"more":[13],"efficient.":[14],"The":[15],"blocking":[16,59,117,162,183],"proposed":[18],"in":[19,76,92,199,207],"literature":[21],"rely":[22],"on":[23,133,185],"homogeneity":[25],"data":[27,46,189],"and":[28,43,165,191],"availability":[30],"binding":[32],"schema":[33],"information;":[34],"thus,":[35],"they":[36],"inapplicable":[38],"to":[39,78,94,118,147,172],"voluminous,":[41],"noisy,":[42],"highly":[44,145],"heterogeneous":[45],"Web":[49],"2.0":[50],"user-generated":[51],"content.":[52],"To":[53],"deal":[54],"with":[55],"such":[56],"data,":[57],"attribute-agnostic":[58,116],"has":[60],"been":[61],"recently":[62],"introduced,":[63],"following":[64],"a":[65,102,125,154,161,196,202],"two-fold":[66],"strategy:":[67],"first":[69],"layer":[70,85,114],"places":[71],"entities":[72],"into":[73,110],"overlapping":[74],"blocks":[75],"order":[77,93],"achieve":[79],"high":[80],"effectiveness,":[81],"while":[82],"second":[84,112],"reduces":[86],"number":[88],"unnecessary":[90],"comparisons":[91,142,178],"enhance":[95],"efficiency.":[96,122],"In":[97],"this":[98],"paper,":[99],"we":[100,135],"present":[101],"set":[103],"techniques":[105,184],"that":[106,127,143,194],"can":[107,169],"be":[108,170],"plugged":[109],"strategy":[113],"further":[119],"improve":[120],"its":[121],"We":[123,151,180],"introduce":[124,153],"technique":[126],"eliminates":[128],"redundant":[129],"comparisons,":[130],"and,":[131],"based":[132],"this,":[134],"incorporate":[136],"an":[137],"approximate":[138],"method":[139,163],"pruning":[141],"likely":[146],"involve":[148],"non-matching":[149],"entities.":[150],"also":[152],"novel":[155],"measure":[156],"quantifying":[158],"redundancy":[160],"entails":[164],"explain":[166],"how":[167],"it":[168],"used":[171],"a-priori":[173],"tune":[174],"process":[176],"pruning.":[179],"apply":[181],"our":[182],"two":[186],"large,":[187],"real-world":[188],"sets":[190],"report":[192],"results":[193],"demonstrate":[195],"substantial":[197],"increase":[198],"efficiency":[200],"at":[201],"negligible":[203],"(if":[204],"any)":[205],"cost":[206],"effectiveness.":[208],"\u00a9":[209],"2011":[210],"ACM.":[211]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
