{"id":"https://openalex.org/W2117974736","doi":"https://doi.org/10.1145/1559845.1559870","title":"Entity resolution with iterative blocking","display_name":"Entity resolution with iterative blocking","publication_year":2009,"publication_date":"2009-06-29","ids":{"openalex":"https://openalex.org/W2117974736","doi":"https://doi.org/10.1145/1559845.1559870","mag":"2117974736"},"language":"en","primary_location":{"id":"doi:10.1145/1559845.1559870","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1559845.1559870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2009 ACM SIGMOD International Conference on Management of data","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/A5012631773","display_name":"Steven Euijong Whang","orcid":"https://orcid.org/0000-0001-6419-931X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Steven Euijong Whang","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084927411","display_name":"David Menestrina","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Menestrina","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012623045","display_name":"Georgia Koutrika","orcid":"https://orcid.org/0000-0002-7377-0116"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Georgia Koutrika","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060837952","display_name":"Martin Theobald","orcid":"https://orcid.org/0000-0003-4067-7609"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Theobald","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055883336","display_name":"H\u00e9ctor Garc\u00eda-Molina","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hector Garcia-Molina","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5012631773"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":21.6626,"has_fulltext":false,"cited_by_count":218,"citation_normalized_percentile":{"value":0.99601687,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"219","last_page":"232"},"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":0.9797000288963318,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9749000072479248,"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/blocking","display_name":"Blocking (statistics)","score":0.9232438802719116},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.803195595741272},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7690649628639221},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5994791984558105},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.5609313249588013},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5226585268974304},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4967232346534729},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.4893159568309784},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4486458897590637},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42672866582870483},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.406051903963089},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.15604233741760254},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10452595353126526},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09256431460380554}],"concepts":[{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.9232438802719116},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.803195595741272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7690649628639221},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5994791984558105},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.5609313249588013},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5226585268974304},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4967232346534729},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.4893159568309784},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4486458897590637},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42672866582870483},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.406051903963089},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.15604233741760254},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10452595353126526},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09256431460380554},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1559845.1559870","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1559845.1559870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2009 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.170.3558","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.170.3558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dc-pubs.dbs.uni-leipzig.de/files/Entity%20resolution%20with%20iterative%20blocking.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.329.7785","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.329.7785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ilpubs.stanford.edu:8090/835/1/2008-19.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.330.5698","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.330.5698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ilpubs.stanford.edu:8090/915/3/sigmod023-whang.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W36024057","https://openalex.org/W154872207","https://openalex.org/W1540269031","https://openalex.org/W1547556487","https://openalex.org/W1569123402","https://openalex.org/W1612155886","https://openalex.org/W1993091968","https://openalex.org/W1997321932","https://openalex.org/W2024770506","https://openalex.org/W2036216970","https://openalex.org/W2046020929","https://openalex.org/W2052390074","https://openalex.org/W2055405704","https://openalex.org/W2067566391","https://openalex.org/W2108991785","https://openalex.org/W2111116800","https://openalex.org/W2117974736","https://openalex.org/W2123561513","https://openalex.org/W2129598390","https://openalex.org/W2138745909","https://openalex.org/W2141634619","https://openalex.org/W2170902582","https://openalex.org/W2171574281","https://openalex.org/W2295665070","https://openalex.org/W4214588406","https://openalex.org/W6632038546","https://openalex.org/W6759150888"],"related_works":["https://openalex.org/W2022562732","https://openalex.org/W2498640783","https://openalex.org/W1495035728","https://openalex.org/W2034475059","https://openalex.org/W2026748623","https://openalex.org/W2185389722","https://openalex.org/W2528330837","https://openalex.org/W2170974505","https://openalex.org/W2360231538","https://openalex.org/W2125467406"],"abstract_inverted_index":{"Entity":[0],"Resolution":[1],"(ER)":[2],"is":[3],"the":[4,15,25,47,53,65,79,94,130,156],"problem":[5],"of":[6,29,49,81,97,133],"identifying":[7],"which":[8,31],"records":[9,54,63],"in":[10,57],"a":[11,152,164],"database":[12],"refer":[13],"to":[14,45,101,119,135],"same":[16,66],"real-world":[17],"entity.":[18],"An":[19],"exhaustive":[20],"ER":[21,50,95,131],"process":[22,72],"involves":[23],"computing":[24],"similarities":[26],"between":[27],"pairs":[28],"records,":[30],"can":[32,42,174],"be":[33,43,147,175],"very":[34],"expensive":[35],"for":[36,159,182],"large":[37,183],"datasets.":[38,184],"Various":[39],"blocking":[40,70,91,123,144,167,173,181],"techniques":[41,71],"used":[44],"enhance":[46],"performance":[48],"by":[51],"dividing":[52],"into":[55],"blocks":[56,73,98,134,137],"multiple":[58],"ways":[59],"and":[60,75,169,178],"only":[61],"comparing":[62],"within":[64],"block.":[67],"However,":[68],"most":[69],"separately":[74],"do":[76],"not":[77],"exploit":[78],"results":[80,96,132],"other":[82,136,160],"blocks.":[83,104,161],"In":[84],"this":[85],"paper,":[86],"we":[87],"propose":[88],"an":[89],"iterative":[90,122,166,172],"framework":[92],"where":[93],"are":[99,106],"reflected":[100],"subsequently":[102],"processed":[103,109],"Blocks":[105],"now":[107,154],"iteratively":[108],"until":[110],"no":[111],"block":[112,153],"contains":[113],"any":[114],"more":[115,148,176],"matching":[116],"records.":[117],"Compared":[118],"simple":[120],"blocking,":[121],"may":[124,138,145],"achieve":[125],"higher":[126],"accuracy":[127],"because":[128,150],"reflecting":[129],"generate":[139],"additional":[140],"record":[141],"matches.":[142],"Iterative":[143],"also":[146],"efficient":[149,179],"processing":[151,157],"saves":[155],"time":[158],"We":[162],"implement":[163],"scalable":[165],"system":[168],"demonstrate":[170],"that":[171],"accurate":[177],"than":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":28},{"year":2015,"cited_by_count":21},{"year":2014,"cited_by_count":20},{"year":2013,"cited_by_count":19},{"year":2012,"cited_by_count":16}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
