{"id":"https://openalex.org/W4288057689","doi":"https://doi.org/10.14778/3538598.3538611","title":"Generalized supervised meta-blocking","display_name":"Generalized supervised meta-blocking","publication_year":2022,"publication_date":"2022-05-01","ids":{"openalex":"https://openalex.org/W4288057689","doi":"https://doi.org/10.14778/3538598.3538611"},"language":"en","primary_location":{"id":"doi:10.14778/3538598.3538611","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3538598.3538611","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":true,"oa_status":"green","oa_url":"https://hdl.handle.net/11380/1278618","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036760548","display_name":"Luca Gagliardelli","orcid":"https://orcid.org/0000-0001-5977-1078"},"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"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Gagliardelli","raw_affiliation_strings":["U. of Modena and Reggio Emilia, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"U. of Modena and Reggio Emilia, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056976720","display_name":"George Papadakis","orcid":"https://orcid.org/0000-0002-7298-9431"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Papadakis","raw_affiliation_strings":["U. of Athens & PPC, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"U. of Athens & PPC, Greece","institution_ids":[]}]},{"author_position":"middle","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"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Simonini","raw_affiliation_strings":["U. of Modena and Reggio Emilia, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"U. of Modena and Reggio Emilia, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","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"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sonia Bergamaschi","raw_affiliation_strings":["U. of Modena and Reggio Emilia, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"U. of Modena and Reggio Emilia, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"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/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 Paris Cit\u00e9 & IUF, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris Cit\u00e9 & IUF, France","institution_ids":["https://openalex.org/I204730241"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6333,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.84609515,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"15","issue":"9","first_page":"1902","last_page":"1910"},"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":0.9932000041007996,"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":0.9837999939918518,"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":0.6454150080680847},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6163257360458374},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.6064390540122986},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.560196042060852},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5027613639831543},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4943404197692871},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.48817020654678345},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44772791862487793},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4376075565814972},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42998653650283813},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36491659283638}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6454150080680847},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6163257360458374},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6064390540122986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.560196042060852},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5027613639831543},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4943404197692871},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.48817020654678345},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44772791862487793},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4376075565814972},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42998653650283813},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36491659283638},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.14778/3538598.3538611","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3538598.3538611","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"},{"id":"pmh:oai:iris.uniecampus.it:11389/69811","is_oa":false,"landing_page_url":"https://hdl.handle.net/11389/69811","pdf_url":null,"source":{"id":"https://openalex.org/S4306400077","display_name":"IRIS eCampus Telematic University (Universit\u00e0 degli Studi eCampus)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I167322064","host_organization_name":"Universit\u00e0 degli Studi eCampus","host_organization_lineage":["https://openalex.org/I167322064"],"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/article"},{"id":"pmh:oai:iris.unimore.it:11380/1278618","is_oa":true,"landing_page_url":"https://hdl.handle.net/11380/1278618","pdf_url":null,"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:iris.unimore.it:11380/1278618","is_oa":true,"landing_page_url":"https://hdl.handle.net/11380/1278618","pdf_url":null,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1504263697","https://openalex.org/W1981590391","https://openalex.org/W2031250218","https://openalex.org/W2079649893","https://openalex.org/W2108087318","https://openalex.org/W2133990480","https://openalex.org/W2139490252","https://openalex.org/W2152502401","https://openalex.org/W2168440643","https://openalex.org/W2210065635","https://openalex.org/W2399361902","https://openalex.org/W2535168187","https://openalex.org/W2751539668","https://openalex.org/W2794107983","https://openalex.org/W2923968079","https://openalex.org/W2925054201","https://openalex.org/W2946741276","https://openalex.org/W3012023689","https://openalex.org/W3014295153","https://openalex.org/W3029269967","https://openalex.org/W3032015135","https://openalex.org/W3092962901","https://openalex.org/W3137039868","https://openalex.org/W4211193898","https://openalex.org/W4283312893"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2108418243","https://openalex.org/W2127804977","https://openalex.org/W164103134","https://openalex.org/W2787352659","https://openalex.org/W2040545019","https://openalex.org/W1970611213","https://openalex.org/W1707372784"],"abstract_inverted_index":{"Entity":[0],"Resolution":[1],"is":[2,105],"a":[3,101,108,124],"core":[4],"data":[5,30],"integration":[6],"task":[7],"that":[8,57,104,126],"relies":[9],"on":[10],"Blocking":[11],"to":[12,14,29,74,107],"scale":[13],"large":[15],"datasets.":[16],"Schema-agnostic":[17],"blocking":[18],"achieves":[19],"very":[20],"high":[21],"recall,":[22],"requires":[23],"no":[24],"domain":[25],"knowledge":[26],"and":[27,34,78],"applies":[28],"of":[31,42,67,121,156,165],"any":[32,131],"structuredness":[33],"schema":[35],"heterogeneity.":[36],"This":[37],"comes":[38],"at":[39],"the":[40,59,82,85,149,161,166],"cost":[41],"many":[43],"irrelevant":[44],"candidate":[45,68],"pairs":[46,66,83],"(i.e.,":[47],"comparisons),":[48],"which":[49],"can":[50,127],"be":[51,128],"significantly":[52],"reduced":[53],"by":[54,94,130],"Meta-blocking":[55,89,117],"techniques":[56],"leverage":[58],"entity":[60],"co-occurrence":[61],"patterns":[62],"inside":[63],"blocks:":[64],"first,":[65],"entities":[69],"are":[70,140],"weighted":[71],"in":[72],"proportion":[73],"their":[75,153],"matching":[76],"likelihood,":[77],"then,":[79],"pruning":[80,132,151],"discards":[81],"with":[84,123],"lowest":[86],"scores.":[87],"Supervised":[88,116],"goes":[90],"beyond":[91],"this":[92],"approach":[93],"combining":[95],"multiple":[96],"scores":[97],"per":[98],"comparison":[99],"into":[100],"feature":[102],"vector":[103],"fed":[106],"binary":[109],"classifier.":[110],"By":[111],"using":[112],"probabilistic":[113],"classifiers,":[114],"Generalized":[115],"associates":[118],"every":[119],"pair":[120],"candidates":[122],"score":[125],"used":[129],"algorithm.":[133],"For":[134],"higher":[135],"effectiveness,":[136],"new":[137],"weighting":[138],"schemes":[139],"examined":[141],"as":[142,158,160],"features.":[143],"Through":[144],"extensive":[145],"experiments,":[146],"we":[147],"identify":[148],"best":[150],"algorithms,":[152],"optimal":[154],"sets":[155],"features,":[157],"well":[159],"minimum":[162],"possible":[163],"size":[164],"training":[167],"set.":[168]},"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":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}