{"id":"https://openalex.org/W3196994458","doi":"https://doi.org/10.3233/idt-200207","title":"SeMBlock: A semantic-aware meta-blocking approach for entity resolution","display_name":"SeMBlock: A semantic-aware meta-blocking approach for entity resolution","publication_year":2021,"publication_date":"2021-09-07","ids":{"openalex":"https://openalex.org/W3196994458","doi":"https://doi.org/10.3233/idt-200207","mag":"3196994458"},"language":"en","primary_location":{"id":"doi:10.3233/idt-200207","is_oa":true,"landing_page_url":"https://doi.org/10.3233/idt-200207","pdf_url":"https://content.iospress.com:443/download/intelligent-decision-technologies/idt200207?id=intelligent-decision-technologies%2Fidt200207","source":{"id":"https://openalex.org/S119727669","display_name":"Intelligent Decision Technologies","issn_l":"1872-4981","issn":["1872-4981","1875-8843"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Decision Technologies","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://content.iospress.com:443/download/intelligent-decision-technologies/idt200207?id=intelligent-decision-technologies%2Fidt200207","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083525709","display_name":"Delaram Javdani","orcid":null},"institutions":[{"id":"https://openalex.org/I67009956","display_name":"Iran University of Science and Technology","ror":"https://ror.org/01jw2p796","country_code":"IR","type":"education","lineage":["https://openalex.org/I67009956"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Delaram Javdani","raw_affiliation_strings":["School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran","institution_ids":["https://openalex.org/I67009956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080786959","display_name":"Hossein Rahmani","orcid":"https://orcid.org/0000-0002-2979-9325"},"institutions":[{"id":"https://openalex.org/I67009956","display_name":"Iran University of Science and Technology","ror":"https://ror.org/01jw2p796","country_code":"IR","type":"education","lineage":["https://openalex.org/I67009956"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Hossein Rahmani","raw_affiliation_strings":["School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran","institution_ids":["https://openalex.org/I67009956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112071698","display_name":"Gerhard Wei\u00df","orcid":"https://orcid.org/0000-0002-6190-2513"},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Gerhard Weiss","raw_affiliation_strings":["Department of Data Science and Knowledge Engineering, Maastricht University, Maastricht, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Data Science and Knowledge Engineering, Maastricht University, Maastricht, The Netherlands","institution_ids":["https://openalex.org/I34352273"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5080786959"],"corresponding_institution_ids":["https://openalex.org/I67009956"],"apc_list":null,"apc_paid":null,"fwci":0.1743,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54177737,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"15","issue":"3","first_page":"461","last_page":"468"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9739000201225281,"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/T11363","display_name":"Dental Radiography and Imaging","score":0.9369000196456909,"subfield":{"id":"https://openalex.org/subfields/3504","display_name":"Oral Surgery"},"field":{"id":"https://openalex.org/fields/35","display_name":"Dentistry"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.756589412689209},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.7370806932449341},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5394675731658936},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5341412425041199},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.49749496579170227},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4927578270435333},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46810293197631836},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4668700397014618},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.412003755569458},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33933913707733154},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.31313949823379517},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14879512786865234},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08689311146736145}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.756589412689209},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.7370806932449341},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5394675731658936},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5341412425041199},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.49749496579170227},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4927578270435333},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46810293197631836},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4668700397014618},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.412003755569458},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33933913707733154},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31313949823379517},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14879512786865234},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08689311146736145},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/idt-200207","is_oa":true,"landing_page_url":"https://doi.org/10.3233/idt-200207","pdf_url":"https://content.iospress.com:443/download/intelligent-decision-technologies/idt200207?id=intelligent-decision-technologies%2Fidt200207","source":{"id":"https://openalex.org/S119727669","display_name":"Intelligent Decision Technologies","issn_l":"1872-4981","issn":["1872-4981","1875-8843"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Decision Technologies","raw_type":"journal-article"},{"id":"pmh:oai:cris.maastrichtuniversity.nl:openaire/087173d8-36bd-4ed2-9e37-2b14f0094ad4","is_oa":true,"landing_page_url":"https://cris.maastrichtuniversity.nl/en/publications/087173d8-36bd-4ed2-9e37-2b14f0094ad4","pdf_url":null,"source":{"id":"https://openalex.org/S4306402616","display_name":"Research Publications (Maastricht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I34352273","host_organization_name":"Maastricht University","host_organization_lineage":["https://openalex.org/I34352273"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Javdani, D, Rahmani, H & Weiss, G 2021, 'SeMBlock: A semantic-aware meta-blocking approach for entity resolution', Intelligent Decision Technologies, vol. 15, no. 3, pp. 461-468. https://doi.org/10.3233/IDT-200207","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.3233/idt-200207","is_oa":true,"landing_page_url":"https://doi.org/10.3233/idt-200207","pdf_url":"https://content.iospress.com:443/download/intelligent-decision-technologies/idt200207?id=intelligent-decision-technologies%2Fidt200207","source":{"id":"https://openalex.org/S119727669","display_name":"Intelligent Decision Technologies","issn_l":"1872-4981","issn":["1872-4981","1875-8843"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Decision Technologies","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3196994458.pdf","grobid_xml":"https://content.openalex.org/works/W3196994458.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W1547612978","https://openalex.org/W1976437052","https://openalex.org/W1992930793","https://openalex.org/W2011940398","https://openalex.org/W2016753842","https://openalex.org/W2027393969","https://openalex.org/W2031250218","https://openalex.org/W2036216970","https://openalex.org/W2073471108","https://openalex.org/W2079649893","https://openalex.org/W2080731889","https://openalex.org/W2111116800","https://openalex.org/W2117974736","https://openalex.org/W2128661986","https://openalex.org/W2132658991","https://openalex.org/W2139490252","https://openalex.org/W2148019918","https://openalex.org/W2152502401","https://openalex.org/W2161936973","https://openalex.org/W2182703380","https://openalex.org/W2202042777","https://openalex.org/W2216499221","https://openalex.org/W2318774417","https://openalex.org/W2398333000","https://openalex.org/W2399361902","https://openalex.org/W2535168187","https://openalex.org/W2548710019","https://openalex.org/W2559870814","https://openalex.org/W2619591136","https://openalex.org/W2771365767","https://openalex.org/W2794107983","https://openalex.org/W2795151173","https://openalex.org/W2796370356","https://openalex.org/W2798649495","https://openalex.org/W2807461918","https://openalex.org/W2809134372","https://openalex.org/W2889154254","https://openalex.org/W2896457183","https://openalex.org/W2922650329","https://openalex.org/W2925156238","https://openalex.org/W2933723051","https://openalex.org/W2933781133","https://openalex.org/W2943447120","https://openalex.org/W2946031341","https://openalex.org/W2946457832","https://openalex.org/W2946741276","https://openalex.org/W2949388608","https://openalex.org/W2950577311","https://openalex.org/W2951345965","https://openalex.org/W2956919901","https://openalex.org/W3003624800","https://openalex.org/W3013609507","https://openalex.org/W3014295153","https://openalex.org/W3021445633","https://openalex.org/W3067852576","https://openalex.org/W3092962901","https://openalex.org/W3097372557","https://openalex.org/W3103649566","https://openalex.org/W3110834397","https://openalex.org/W4242744113","https://openalex.org/W4254788633","https://openalex.org/W4300444796","https://openalex.org/W6679268411","https://openalex.org/W6683401941"],"related_works":["https://openalex.org/W2392835431","https://openalex.org/W1965371215","https://openalex.org/W2126932387","https://openalex.org/W1555349535","https://openalex.org/W1556451512","https://openalex.org/W2353762239","https://openalex.org/W2484966135","https://openalex.org/W2015050211","https://openalex.org/W4234091740","https://openalex.org/W2108990487"],"abstract_inverted_index":{"Entity":[0],"resolution":[1],"refers":[2],"to":[3,13,30,39,87,147],"the":[4,47,73,100,103,117],"process":[5],"of":[6,27,76,102,111,159],"identifying,":[7],"matching,":[8],"and":[9,90,115,152,156,164],"integrating":[10],"records":[11,28,77,114],"belonging":[12],"unique":[14],"entities":[15,42],"in":[16,93],"a":[17,21,65,94,108],"data":[18,96,132],"set.":[19],"However,":[20],"comprehensive":[22],"comparison":[23],"across":[24],"all":[25,142],"pairs":[26],"leads":[29],"quadratic":[31],"matching":[32],"complexity.":[33],"Therefore,":[34],"blocking":[35,50,92,127,171],"methods":[36,51,144],"are":[37,161],"used":[38],"group":[40],"similar":[41,113],"into":[43],"small":[44],"blocks":[45,104],"before":[46],"matching.":[48],"Available":[49],"typically":[52],"do":[53],"not":[54],"consider":[55],"semantic":[56,74],"relationships":[57],"among":[58],"records.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63],"propose":[64],"Semantic-aware":[66],"Meta-Blocking":[67],"approach":[68],"called":[69],"SeMBlock.":[70],"SeMBlock":[71,106,123,139,160],"considers":[72],"similarity":[75],"by":[78],"applying":[79],"locality-sensitive":[80],"hashing":[81],"(LSH)":[82],"based":[83],"on":[84],"word":[85],"embedding":[86],"achieve":[88],"fast":[89],"reliable":[91],"large-scale":[95],"environment.":[97],"To":[98],"improve":[99],"quality":[101],"created,":[105],"builds":[107],"weighted":[109],"graph":[110,118],"semantically":[112],"prunes":[116],"edges.":[119],"We":[120],"extensively":[121],"compare":[122],"with":[124,145],"16":[125,143],"existing":[126],"methods,":[128],"using":[129],"three":[130],"real-world":[131],"sets.":[133],"The":[134],"experimental":[135],"results":[136],"show":[137],"that":[138],"significantly":[140],"outperforms":[141],"respect":[146],"two":[148],"relevant":[149],"measures,":[150],"F-measure":[151,155],"pair-quality":[153,157],"measure.":[154],"measure":[158],"approximately":[162],"7%":[163],"27%,":[165],"respectively,":[166],"higher":[167],"than":[168],"recently":[169],"released":[170],"methods.":[172]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}