{"id":"https://openalex.org/W2139490252","doi":"https://doi.org/10.14778/2733085.2733098","title":"Supervised meta-blocking","display_name":"Supervised meta-blocking","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2139490252","doi":"https://doi.org/10.14778/2733085.2733098","mag":"2139490252"},"language":"en","primary_location":{"id":"doi:10.14778/2733085.2733098","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2733085.2733098","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/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":true,"raw_author_name":"George Papadakis","raw_affiliation_strings":["Research Center, Athena, Greece"],"affiliations":[{"raw_affiliation_string":"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":["Research Center, Athena, Greece"],"affiliations":[{"raw_affiliation_string":"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","HP Labs,"],"affiliations":[{"raw_affiliation_string":"HP Labs","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"HP Labs,","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056976720"],"corresponding_institution_ids":["https://openalex.org/I4210156054"],"apc_list":null,"apc_paid":null,"fwci":5.2756,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.95555622,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"7","issue":"14","first_page":"1929","last_page":"1940"},"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":0.9793999791145325,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9661999940872192,"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":0.8221144080162048},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.7893862724304199},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.719954252243042},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6120225787162781},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6011269092559814},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5579090118408203},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5537247061729431},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5045591592788696},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47643882036209106},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46730825304985046},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.4313521385192871},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.410077840089798},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09240704774856567}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8221144080162048},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.7893862724304199},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.719954252243042},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6120225787162781},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6011269092559814},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5579090118408203},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5537247061729431},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5045591592788696},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47643882036209106},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46730825304985046},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.4313521385192871},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.410077840089798},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09240704774856567},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/2733085.2733098","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2733085.2733098","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:CiteSeerX.psu:10.1.1.657.5718","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.657.5718","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.vldb.org/pvldb/vol7/p1929-papadakis.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1540269031","https://openalex.org/W1570448133","https://openalex.org/W1623006543","https://openalex.org/W1995099886","https://openalex.org/W1998475090","https://openalex.org/W2011940398","https://openalex.org/W2024770506","https://openalex.org/W2029554959","https://openalex.org/W2031250218","https://openalex.org/W2036216970","https://openalex.org/W2065398649","https://openalex.org/W2067566391","https://openalex.org/W2079649893","https://openalex.org/W2088008685","https://openalex.org/W2102763740","https://openalex.org/W2109834209","https://openalex.org/W2111116800","https://openalex.org/W2111625757","https://openalex.org/W2117974736","https://openalex.org/W2132658991","https://openalex.org/W2152502401","https://openalex.org/W2154785834","https://openalex.org/W2158418361","https://openalex.org/W2161600801","https://openalex.org/W2161936973","https://openalex.org/W2164456230","https://openalex.org/W2966207845"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W2583394830","https://openalex.org/W2783385843","https://openalex.org/W4306674287","https://openalex.org/W4319309271","https://openalex.org/W2355215981","https://openalex.org/W3199608561","https://openalex.org/W2365088826","https://openalex.org/W2963260880","https://openalex.org/W2139490252"],"abstract_inverted_index":{"Entity":[0,39],"Resolution":[1],"matches":[2],"mentions":[3],"of":[4,38,55,121],"the":[5,31,36,53],"same":[6,32],"entity.":[7],"Being":[8],"an":[9],"expensive":[10],"task":[11],"for":[12,109],"large":[13],"data,":[14],"its":[15,49],"performance":[16,142],"can":[17,82,139,148],"be":[18,83,149],"improved":[19],"by":[20],"blocking,":[21],"i.e.,":[22],"grouping":[23],"similar":[24],"entities":[25,29],"and":[26,160,169],"comparing":[27],"only":[28],"in":[30,60],"group.":[33],"Blocking":[34],"improves":[35],"run-time":[37],"Resolution,":[40],"but":[41],"it":[42],"still":[43],"involves":[44],"unnecessary":[45,89],"comparisons":[46],"that":[47,81,105,124,136,147],"limit":[48],"performance.":[50],"Meta-blocking":[51],"is":[52],"process":[54],"restructuring":[56],"a":[57,76,118,126],"block":[58],"collection":[59],"order":[61],"to":[62],"prune":[63],"such":[64],"comparisons.":[65,112],"Existing":[66],"unsupervised":[67],"meta-blocking":[68,103,138],"methods":[69,162],"use":[70],"simple":[71],"pruning":[72,94],"rules,":[73],"which":[74],"offer":[75],"rather":[77],"coarse-grained":[78],"filtering":[79],"technique":[80],"conservative":[84],"(i.e.,":[85,93],"keeping":[86],"too":[87],"many":[88],"comparisons)":[90],"or":[91],"aggressive":[92],"good":[95],"comparisons).":[96],"In":[97],"this":[98,114],"work,":[99],"we":[100,116],"introduce":[101],"supervised":[102,137,156],"techniques":[104],"learn":[106],"classification":[107],"models":[108],"distinguishing":[110],"promising":[111],"For":[113],"task,":[115],"propose":[117],"small":[119,144],"set":[120],"generic":[122],"features":[123],"combine":[125],"low":[127],"extraction":[128],"cost":[129],"with":[130,143,158],"high":[131,141],"discriminatory":[132],"power.":[133],"We":[134,152],"show":[135],"achieve":[140],"training":[145],"sets":[146],"manually":[150],"created.":[151],"analytically":[153],"compare":[154],"our":[155],"approaches":[157],"baseline":[159],"competitor":[161],"over":[163],"10":[164],"large-scale":[165],"datasets,":[166],"both":[167],"real":[168],"synthetic.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}