{"id":"https://openalex.org/W2032327675","doi":"https://doi.org/10.1145/1066157.1066287","title":"Data cleaning in microsoft SQL server 2005","display_name":"Data cleaning in microsoft SQL server 2005","publication_year":2005,"publication_date":"2005-06-14","ids":{"openalex":"https://openalex.org/W2032327675","doi":"https://doi.org/10.1145/1066157.1066287","mag":"2032327675"},"language":"en","primary_location":{"id":"doi:10.1145/1066157.1066287","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1066157.1066287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 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/A5038037154","display_name":"Surajit Chaudhuri","orcid":"https://orcid.org/0000-0001-8252-5270"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Surajit Chaudhuri","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080534589","display_name":"Kris Ganjam","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kris Ganjam","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049419417","display_name":"Venky Ganti","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venky Ganti","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010600636","display_name":"Rahul Kapoor","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahul Kapoor","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063257827","display_name":"Vivek Narasayya","orcid":"https://orcid.org/0000-0001-7011-7886"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vivek Narasayya","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075907703","display_name":"Theo Vassilakis","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Theo Vassilakis","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.6489,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.94648848,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"918","last_page":"920"},"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":0.992900013923645,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9886999726295471,"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":0.8356809616088867},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.5844066739082336},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5259647369384766},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.514819324016571},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.511246919631958},{"id":"https://openalex.org/keywords/language-integrated-query","display_name":"Language Integrated Query","score":0.5090174674987793},{"id":"https://openalex.org/keywords/online-analytical-processing","display_name":"Online analytical processing","score":0.4978666305541992},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4818885922431946},{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.4751332104206085},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4588537812232971},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.44806021451950073},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.43647003173828125},{"id":"https://openalex.org/keywords/data-transformation-services","display_name":"Data Transformation Services","score":0.4163532555103302},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3008408546447754},{"id":"https://openalex.org/keywords/query-by-example","display_name":"Query by Example","score":0.17880067229270935},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.10763472318649292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.08913305401802063},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.0873541533946991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8356809616088867},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.5844066739082336},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5259647369384766},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.514819324016571},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.511246919631958},{"id":"https://openalex.org/C179531526","wikidata":"https://www.wikidata.org/wiki/Q595637","display_name":"Language Integrated Query","level":5,"score":0.5090174674987793},{"id":"https://openalex.org/C201932085","wikidata":"https://www.wikidata.org/wiki/Q642514","display_name":"Online analytical processing","level":3,"score":0.4978666305541992},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4818885922431946},{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.4751332104206085},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4588537812232971},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.44806021451950073},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.43647003173828125},{"id":"https://openalex.org/C141589383","wikidata":"https://www.wikidata.org/wiki/Q644775","display_name":"Data Transformation Services","level":5,"score":0.4163532555103302},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3008408546447754},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.17880067229270935},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.10763472318649292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08913305401802063},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0873541533946991},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1066157.1066287","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1066157.1066287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2024770506","https://openalex.org/W2105423800"],"related_works":["https://openalex.org/W2383619981","https://openalex.org/W4390861444","https://openalex.org/W2485151021","https://openalex.org/W2461902653","https://openalex.org/W4206687279","https://openalex.org/W3215879106","https://openalex.org/W2515107547","https://openalex.org/W1606045526","https://openalex.org/W1144128981","https://openalex.org/W2365864249"],"abstract_inverted_index":{"When":[0],"collecting":[1],"and":[2,16,64,75,92,102,122],"combining":[3],"data":[4,10,14,25,30,40,56,73,87,136],"from":[5],"various":[6],"sources":[7,33],"into":[8],"a":[9,19,100],"warehouse,":[11],"ensuring":[12],"high":[13,135],"quality":[15,26],"consistency":[17],"becomes":[18],"significant,":[20],"often":[21],"expensive,":[22],"challenge.":[23],"Common":[24],"problems":[27,98],"include":[28],"inconsistent":[29],"conventions":[31],"amongst":[32],"such":[34,43],"as":[35,44,61],"different":[36],"abbreviations":[37],"or":[38,50,81],"synonyms;":[39],"entry":[41],"errors":[42],"spelling":[45],"mistakes;":[46],"missing,":[47],"incomplete,":[48],"outdated":[49],"otherwise":[51],"incorrect":[52],"attribute":[53],"values.":[54],"These":[55,105],"defects":[57],"generally":[58],"manifest":[59],"themselves":[60],"foreign-key":[62],"mismatches":[63],"approximately":[65],"duplicate":[66],"records,":[67],"both":[68],"of":[69],"which":[70,95,128],"make":[71],"further":[72],"mining":[74],"decision":[76],"support":[77],"analyses":[78],"either":[79],"impossible":[80],"suspect.":[82],"We":[83],"demonstrate":[84],"two":[85],"new":[86],"cleansing":[88],"operators,":[89],"Fuzzy":[90,93],"Lookup":[91],"Grouping,":[94],"address":[96],"these":[97],"in":[99,127],"scalable":[101],"domain-independent":[103],"manner.":[104],"operators":[106],"are":[107],"implemented":[108],"within":[109],"Microsoft":[110],"SQL":[111],"Server":[112],"2005":[113],"Integration":[114],"Services.":[115],"Our":[116],"demo":[117],"will":[118],"explain":[119],"their":[120],"functionality":[121],"highlight":[123],"multiple":[124],"real-world":[125],"scenarios":[126],"they":[129],"can":[130],"be":[131],"used":[132],"to":[133],"achieve":[134],"quality.":[137]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}