{"id":"https://openalex.org/W4229032192","doi":"https://doi.org/10.1145/3477314.3507689","title":"A graph-based blocking approach for entity matching using pre-trained contextual embedding models","display_name":"A graph-based blocking approach for entity matching using pre-trained contextual embedding models","publication_year":2022,"publication_date":"2022-04-25","ids":{"openalex":"https://openalex.org/W4229032192","doi":"https://doi.org/10.1145/3477314.3507689"},"language":"en","primary_location":{"id":"doi:10.1145/3477314.3507689","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477314.3507689","pdf_url":null,"source":{"id":"https://openalex.org/S4363608665","display_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-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/A5070857951","display_name":"John Bosco Mugeni","orcid":"https://orcid.org/0000-0002-2464-413X"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"John Bosco Mugeni","raw_affiliation_strings":["University of Tsukuba, Tsukuba, Ibaraki"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, Ibaraki","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025604052","display_name":"Toshiyuki Amagasa","orcid":"https://orcid.org/0000-0003-0595-2230"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshiyuki Amagasa","raw_affiliation_strings":["University of Tsukuba, Tsukuba, Ibaraki"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, Ibaraki","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5070857951"],"corresponding_institution_ids":["https://openalex.org/I146399215"],"apc_list":null,"apc_paid":null,"fwci":0.2573,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36904124,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"357","last_page":"364"},"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":0.9817000031471252,"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/T10028","display_name":"Topic Modeling","score":0.9283999800682068,"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":0.752726137638092},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5143471956253052},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5021545886993408},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.5010859966278076},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4912554621696472},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4837927520275116},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4582142233848572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4165850281715393},{"id":"https://openalex.org/keywords/clustering-coefficient","display_name":"Clustering coefficient","score":0.41218075156211853},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3288114070892334},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12767115235328674}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.752726137638092},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5143471956253052},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5021545886993408},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.5010859966278076},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4912554621696472},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4837927520275116},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4582142233848572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4165850281715393},{"id":"https://openalex.org/C22047676","wikidata":"https://www.wikidata.org/wiki/Q898680","display_name":"Clustering coefficient","level":3,"score":0.41218075156211853},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3288114070892334},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12767115235328674},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3477314.3507689","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477314.3507689","pdf_url":null,"source":{"id":"https://openalex.org/S4363608665","display_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2131681506","https://openalex.org/W2544062944","https://openalex.org/W2612690371","https://openalex.org/W2794291661","https://openalex.org/W2798649495","https://openalex.org/W2897249806","https://openalex.org/W2945883855","https://openalex.org/W2966720878","https://openalex.org/W3011807731","https://openalex.org/W3014295153","https://openalex.org/W3096174636","https://openalex.org/W3106188259","https://openalex.org/W3155638005"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2392835431"],"abstract_inverted_index":{"Data":[0],"integration":[1],"is":[2,37,49,117],"considered":[3],"a":[4,32,60,81,85,111],"crucial":[5],"task":[6],"in":[7,128,138,195],"the":[8,26,120,132,139,146,176,181],"entity":[9,126],"matching":[10,127],"process.":[11],"In":[12],"this":[13,40,105],"process,":[14],"redundant":[15],"and":[16,22,83,107,131],"cunning":[17],"entries":[18],"must":[19],"be":[20],"identified":[21],"eliminated":[23],"to":[24,51,54,80,172,175,202],"improve":[25],"data":[27,124,154,178],"quality.":[28],"To":[29,45],"archive":[30],"this,":[31,47],"comparison":[33],"between":[34],"all":[35],"entities":[36],"performed.":[38],"However,":[39],"has":[41],"quadratic":[42],"computational":[43],"complexity.":[44],"avoid":[46],"'blocking'":[48],"introduced":[50],"limit":[52],"comparisons":[53],"probable":[55],"matches.":[56],"This":[57],"paper":[58],"presents":[59],"k-nearest":[61,182],"neighbor":[62,183],"graph-based":[63],"blocking":[64,109,136,150,206],"approach":[65,75],"utilizing":[66],"state-of-the-art":[67],"context-aware":[68],"sentence":[69],"embeddings":[70],"from":[71,170],"pre-trained":[72],"transformers.":[73],"Our":[74,115,185],"maps":[76],"each":[77],"database":[78],"tuple":[79],"node":[82],"generates":[84],"graph":[86,106,112],"where":[87],"nodes":[88],"are":[89,95],"connected":[90],"by":[91,119],"edges":[92],"if":[93],"they":[94],"related.":[96],"We":[97,144,162],"then":[98],"invoke":[99],"unsupervised":[100],"community":[101],"detection":[102],"techniques":[103],"over":[104],"treat":[108],"as":[110],"clustering":[113],"problem.":[114],"work":[116],"motivated":[118],"scarcity":[121],"of":[122,135,141,148,180,197],"training":[123],"for":[125],"real-world":[129],"scenarios":[130],"limited":[133],"scalability":[134],"schemes":[137],"presence":[140],"proliferating":[142],"data.":[143],"test":[145],"capabilities":[147],"our":[149,165,190],"system":[151],"on":[152],"four":[153],"sets":[155],"exhibiting":[156],"more":[157],"than":[158],"6":[159],"million":[160],"comparisons.":[161],"show":[163,188],"that":[164,189],"block":[166],"processing":[167],"times":[168],"vary":[169],"59s":[171],"461s":[173],"owing":[174],"efficient":[177],"structure":[179],"graph.":[184],"results":[186],"also":[187],"method":[191],"achieves":[192],"better":[193],"performance":[194],"terms":[196],"F1":[198],"score":[199],"when":[200],"compared":[201],"current":[203],"deep":[204],"learning-based":[205],"solutions.":[207]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}