{"id":"https://openalex.org/W2135878030","doi":"https://doi.org/10.1109/icde.2008.4497420","title":"Validating Multi-column Schema Matchings by Type","display_name":"Validating Multi-column Schema Matchings by Type","publication_year":2008,"publication_date":"2008-04-01","ids":{"openalex":"https://openalex.org/W2135878030","doi":"https://doi.org/10.1109/icde.2008.4497420","mag":"2135878030"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2008.4497420","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2008.4497420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE 24th International Conference on Data Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ink.library.smu.edu.sg/sis_research/4167","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081863278","display_name":"Bing Tian Dai","orcid":"https://orcid.org/0000-0002-7245-7021"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bing Tian Dai","raw_affiliation_strings":["National University of Singapore, Singapore, Republic of Singapore","Nat. Univ. of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Republic of Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Nat. Univ. of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035257754","display_name":"Nick Koudas","orcid":"https://orcid.org/0000-0001-5648-0638"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA","SG"],"is_corresponding":false,"raw_author_name":"Nick Koudas","raw_affiliation_strings":["University of Toronto, Toronto, Canada","Nat. Univ. of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Nat. Univ. of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088315797","display_name":"Divesh Srivastava","orcid":"https://orcid.org/0000-0002-7609-9217"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Divesh Srivastava","raw_affiliation_strings":["National University of Singapore, Singapore, SG","Nat. Univ. of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, SG","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Nat. Univ. of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023925931","display_name":"Anthony K. H. Tung","orcid":"https://orcid.org/0000-0002-5125-855X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Anthony K. H. Tung","raw_affiliation_strings":["National University of Singapore, Singapore, Republic of Singapore","Nat. Univ. of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Republic of Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Nat. Univ. of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061790878","display_name":"Suresh Venkatasubramanian","orcid":"https://orcid.org/0000-0001-7679-7130"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["SG","US"],"is_corresponding":false,"raw_author_name":"Suresh Venkatasubramanian","raw_affiliation_strings":["University of Utah, Salt Lake City, USA","Nat. Univ. of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, USA","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"Nat. Univ. of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"120","last_page":"129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9991000294685364,"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/T11719","display_name":"Data Quality and Management","score":0.9987999796867371,"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":0.9987000226974487,"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/schema-matching","display_name":"Schema matching","score":0.9201043844223022},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6989884376525879},{"id":"https://openalex.org/keywords/conceptual-schema","display_name":"Conceptual schema","score":0.5841134190559387},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5469406843185425},{"id":"https://openalex.org/keywords/database-schema","display_name":"Database schema","score":0.5328161120414734},{"id":"https://openalex.org/keywords/star-schema","display_name":"Star schema","score":0.5111058354377747},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.484894335269928},{"id":"https://openalex.org/keywords/semi-structured-model","display_name":"Semi-structured model","score":0.4487428367137909},{"id":"https://openalex.org/keywords/schema-migration","display_name":"Schema migration","score":0.41769102215766907},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3489915132522583},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.33138126134872437},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3052012324333191},{"id":"https://openalex.org/keywords/database-design","display_name":"Database design","score":0.15268400311470032}],"concepts":[{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.9201043844223022},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6989884376525879},{"id":"https://openalex.org/C29275276","wikidata":"https://www.wikidata.org/wiki/Q2268965","display_name":"Conceptual schema","level":3,"score":0.5841134190559387},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5469406843185425},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.5328161120414734},{"id":"https://openalex.org/C190703929","wikidata":"https://www.wikidata.org/wiki/Q1331138","display_name":"Star schema","level":4,"score":0.5111058354377747},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.484894335269928},{"id":"https://openalex.org/C56310702","wikidata":"https://www.wikidata.org/wiki/Q2269281","display_name":"Semi-structured model","level":4,"score":0.4487428367137909},{"id":"https://openalex.org/C153440673","wikidata":"https://www.wikidata.org/wiki/Q7431119","display_name":"Schema migration","level":5,"score":0.41769102215766907},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3489915132522583},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.33138126134872437},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3052012324333191},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.15268400311470032},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.0},{"id":"https://openalex.org/C165611974","wikidata":"https://www.wikidata.org/wiki/Q5531015","display_name":"Gender schema theory","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icde.2008.4497420","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2008.4497420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE 24th International Conference on Data Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/41438","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/41438","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus","raw_type":"Conference Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.151.7967","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.151.7967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.comp.nus.edu.sg/~atung/publication/validate_icde08.pdf","raw_type":"text"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-5170","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/4167","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/ICDE.2008.4497420","raw_type":"Conference Proceeding Article"}],"best_oa_location":{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-5170","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/4167","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1109/ICDE.2008.4497420","raw_type":"Conference Proceeding Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1520363973","https://openalex.org/W1536941882","https://openalex.org/W1570448133","https://openalex.org/W1686946872","https://openalex.org/W1818506960","https://openalex.org/W2008896880","https://openalex.org/W2021739502","https://openalex.org/W2027780984","https://openalex.org/W2042389627","https://openalex.org/W2077296695","https://openalex.org/W2099111195","https://openalex.org/W2117418278","https://openalex.org/W2127753549","https://openalex.org/W2138745488","https://openalex.org/W2139135093","https://openalex.org/W2146950091","https://openalex.org/W2150365753","https://openalex.org/W2152111724","https://openalex.org/W2159833638","https://openalex.org/W2163372266","https://openalex.org/W2168996210","https://openalex.org/W2979454998","https://openalex.org/W3004104752","https://openalex.org/W4238783465","https://openalex.org/W4243227447","https://openalex.org/W6637108112","https://openalex.org/W6655770780","https://openalex.org/W6679053554","https://openalex.org/W6680506379","https://openalex.org/W6683507319","https://openalex.org/W6684885842"],"related_works":["https://openalex.org/W945629821","https://openalex.org/W1971380397","https://openalex.org/W2766698234","https://openalex.org/W1499427961","https://openalex.org/W2584207435","https://openalex.org/W2954497382","https://openalex.org/W2131981997","https://openalex.org/W2353410322","https://openalex.org/W896179304","https://openalex.org/W3030019037"],"abstract_inverted_index":{"Validation":[0],"of":[1,36,110,191,197],"multi-column":[2],"schema":[3,52,80,104,157,172],"matchings":[4],"is":[5,13,27,84],"essential":[6],"for":[7,75,97,123,131],"successful":[8],"database":[9,198],"integration.":[10],"This":[11],"task":[12],"especially":[14],"difficult":[15],"when":[16],"the":[17,29,41,115,121,133,148,187],"databases":[18],"to":[19,139,145,169],"be":[20,63],"integrated":[21],"contain":[22],"little":[23],"overlapping":[24],"data,":[25],"as":[26],"often":[28],"case":[30],"in":[31,46,136,150],"practice":[32],"(e.g.,":[33],"customer":[34],"bases":[35],"different":[37,47],"companies).":[38],"Based":[39],"on":[40,86,107,194],"intuition":[42],"that":[43,60,113,142,185],"values":[44,68,135,149],"present":[45,128],"columns":[48,100],"related":[49],"by":[50,102],"a":[51,73,94,103,108,137,171,195],"matching":[53],"will":[54],"have":[55],"similar":[56],"\"semantic":[57],"type\",":[58],"and":[59,78,178,189,200],"this":[61,119,153],"can":[62],"captured":[64],"using":[65],"distributions":[66],"over":[67],"(\"statistical":[69],"types\"),":[70],"we":[71,92,127],"develop":[72],"method":[74],"validating":[76],"1-1":[77],"compositional":[79],"matchings.":[81],"Our":[82],"technique":[83,161,193],"based":[85,106],"three":[87],"key":[88],"technical":[89],"ideas.":[90],"First,":[91],"propose":[93],"generic":[95],"measure":[96],"comparing":[98],"two":[99],"matched":[101],"matching,":[105],"notion":[109],"information-theoretic":[111],"discrepancy":[112],"generalizes":[114],"standard":[116],"geometric":[117],"discrepancy;":[118],"provides":[120,162],"basis":[122],"1:1":[124],"matching.":[125,158,173],"Second,":[126],"an":[129,163,182],"algorithm":[130],"\"splitting\"":[132],"string":[134],"column":[138],"identify":[140],"substrings":[141],"are":[143],"likely":[144],"match":[146],"with":[147,181],"another":[151],"column;":[152],"enables":[154],"(multi-column)":[155],"1:m":[156],"Third,":[159],"our":[160,176,192],"invalidation":[164],"certificate":[165],"if":[166],"it":[167],"fails":[168],"validate":[170],"We":[174],"complement":[175],"conceptual":[177],"algorithmic":[179],"contributions":[180],"experimental":[183],"study":[184],"demonstrates":[186],"effectiveness":[188],"efficiency":[190],"variety":[196],"schemas":[199],"data":[201],"sets.":[202]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
