{"id":"https://openalex.org/W2023703869","doi":"https://doi.org/10.1145/1807167.1807177","title":"Sampling dirty data for matching attributes","display_name":"Sampling dirty data for matching attributes","publication_year":2010,"publication_date":"2010-06-06","ids":{"openalex":"https://openalex.org/W2023703869","doi":"https://doi.org/10.1145/1807167.1807177","mag":"2023703869"},"language":"en","primary_location":{"id":"doi:10.1145/1807167.1807177","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 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/A5010236208","display_name":"Henning K\u00f6hler","orcid":null},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Henning K\u00f6hler","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011384237","display_name":"Xiaofang Zhou","orcid":"https://orcid.org/0000-0001-6343-1455"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaofang Zhou","raw_affiliation_strings":["The University of Queensland and NICTA, Brisbane, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Queensland and NICTA, Brisbane, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070591850","display_name":"Shazia Sadiq","orcid":"https://orcid.org/0000-0001-6739-4145"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shazia Sadiq","raw_affiliation_strings":["The University of Queensland, Brisbane, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070864647","display_name":"Yanfeng Shu","orcid":null},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yanfeng Shu","raw_affiliation_strings":["CSIRO - Tasmanian ICT Centre, Hobart, Australia","CSIRO - Tasmanian ICT Centre, Hobart, Australia#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSIRO - Tasmanian ICT Centre, Hobart, Australia","institution_ids":["https://openalex.org/I1292875679"]},{"raw_affiliation_string":"CSIRO - Tasmanian ICT Centre, Hobart, Australia#TAB#","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011393580","display_name":"Kerry Taylor","orcid":"https://orcid.org/0000-0003-2447-1088"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Kerry Taylor","raw_affiliation_strings":["CSIRO - ICT Centre, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSIRO - ICT Centre, Canberra, Australia","institution_ids":["https://openalex.org/I1292875679"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8178,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.94666813,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"63","last_page":"74"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9975000023841858,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.8228148221969604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7463396191596985},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7332730293273926},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.66798996925354},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6007319688796997},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5423129796981812},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5126301646232605},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.49677902460098267},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4932021498680115},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.42920249700546265},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2718466818332672},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18220004439353943},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09444424510002136},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.07152369618415833}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.8228148221969604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7463396191596985},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7332730293273926},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.66798996925354},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6007319688796997},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5423129796981812},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5126301646232605},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.49677902460098267},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4932021498680115},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.42920249700546265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2718466818332672},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18220004439353943},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09444424510002136},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.07152369618415833},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1807167.1807177","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.165.4583","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.165.4583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.itee.uq.edu.au/%7Ezxf/_papers/sigmod108-koehler.pdf","raw_type":"text"},{"id":"pmh:oai:repository.ust.hk:1783.1-108414","is_oa":false,"landing_page_url":"http://repository.ust.hk/ir/Record/1783.1-108414","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W72943092","https://openalex.org/W1556076816","https://openalex.org/W1570528139","https://openalex.org/W1592355944","https://openalex.org/W1609518033","https://openalex.org/W1964857063","https://openalex.org/W1984566373","https://openalex.org/W1995875735","https://openalex.org/W2008896880","https://openalex.org/W2029554959","https://openalex.org/W2029815943","https://openalex.org/W2038281398","https://openalex.org/W2041404167","https://openalex.org/W2041912938","https://openalex.org/W2042558865","https://openalex.org/W2059268928","https://openalex.org/W2090403603","https://openalex.org/W2108991785","https://openalex.org/W2110686900","https://openalex.org/W2119057313","https://openalex.org/W2132069633","https://openalex.org/W2135878030","https://openalex.org/W2140313762","https://openalex.org/W2142151675","https://openalex.org/W2147232895","https://openalex.org/W2148885851","https://openalex.org/W2151065878","https://openalex.org/W2152565070","https://openalex.org/W2161936973","https://openalex.org/W2199389590","https://openalex.org/W2993383518","https://openalex.org/W4237172715","https://openalex.org/W4250212406","https://openalex.org/W6633446409","https://openalex.org/W6635371082","https://openalex.org/W6681013973","https://openalex.org/W6683401941"],"related_works":["https://openalex.org/W2088925915","https://openalex.org/W2382891957","https://openalex.org/W2393491644","https://openalex.org/W2067184662","https://openalex.org/W3047837489","https://openalex.org/W2622139626","https://openalex.org/W2133660117","https://openalex.org/W2104496206","https://openalex.org/W3013303285","https://openalex.org/W2385836742"],"abstract_inverted_index":{"We":[0],"investigate":[1],"the":[2,80,139],"problem":[3],"of":[4,9,63],"creating":[5],"and":[6,91,126],"analyzing":[7],"samples":[8],"relational":[10],"databases":[11],"to":[12],"find":[13],"relationships":[14],"between":[15,61,75,124],"string-valued":[16],"attributes.":[17,36],"Our":[18],"focus":[19],"is":[20,120],"on":[21,138],"identifying":[22],"attribute":[23],"pairs":[24],"whose":[25],"value":[26,108],"sets":[27,40,62],"overlap,":[28],"a":[29,121,130],"pre-condition":[30],"for":[31,87,98,106],"typical":[32],"joins":[33],"over":[34],"such":[35],"However,":[37],"real-world":[38],"data":[39,47,100],"are":[41,103],"often":[42],"'dirty',":[43],"especially":[44],"when":[45],"integrating":[46],"from":[48],"different":[49],"sources.":[50],"To":[51,78],"deal":[52],"with":[53,134],"this":[54],"issue,":[55],"we":[56,83,115],"propose":[57],"new":[58],"similarity":[59,74,92],"measures":[60,81,102,136],"strings,":[64],"which":[65],"not":[66],"only":[67],"consider":[68],"set":[69],"based":[70],"similarity,":[71],"but":[72,114],"also":[73,116],"strings":[76],"instances.":[77],"make":[79],"effective,":[82],"develop":[84],"efficient":[85],"algorithms":[86],"distributed":[88],"sample":[89],"creation":[90],"computation.":[93],"Test":[94],"results":[95],"show":[96],"that":[97,118],"dirty":[99],"our":[101],"more":[104],"accurate":[105],"measuring":[107],"overlap":[109],"than":[110],"existing":[111],"sample-based":[112],"methods,":[113],"observe":[117],"there":[119],"clear":[122],"tradeoff":[123],"accuracy":[125],"speed.":[127],"This":[128],"motivates":[129],"two-stage":[131],"filtering":[132],"approach,":[133],"both":[135],"operating":[137],"same":[140],"samples.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}