{"id":"https://openalex.org/W2157631542","doi":"https://doi.org/10.1145/1807167.1807213","title":"Schema clustering and retrieval for multi-domain pay-as-you-go data integration systems","display_name":"Schema clustering and retrieval for multi-domain pay-as-you-go data integration systems","publication_year":2010,"publication_date":"2010-06-06","ids":{"openalex":"https://openalex.org/W2157631542","doi":"https://doi.org/10.1145/1807167.1807213","mag":"2157631542"},"language":"en","primary_location":{"id":"doi:10.1145/1807167.1807213","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807213","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/A5108207058","display_name":"Hatem A. Mahmoud","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hatem A. Mahmoud","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000416532","display_name":"Ashraf Aboulnaga","orcid":"https://orcid.org/0000-0001-6693-7099"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ashraf Aboulnaga","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.5937,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.95812731,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"411","last_page":"422"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9990000128746033,"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":0.9990000128746033,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9987999796867371,"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/computer-science","display_name":"Computer science","score":0.8209283351898193},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.7136183381080627},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.629920244216919},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5833665132522583},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5753487348556519},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5629779100418091},{"id":"https://openalex.org/keywords/conceptual-schema","display_name":"Conceptual schema","score":0.41767618060112},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.4146268367767334},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4103918671607971},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23670175671577454},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20211666822433472}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8209283351898193},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.7136183381080627},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.629920244216919},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5833665132522583},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5753487348556519},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5629779100418091},{"id":"https://openalex.org/C29275276","wikidata":"https://www.wikidata.org/wiki/Q2268965","display_name":"Conceptual schema","level":3,"score":0.41767618060112},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.4146268367767334},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4103918671607971},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23670175671577454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20211666822433472},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1807167.1807213","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807213","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:10.1.1.392.5027","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.392.5027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://cs.uwaterloo.ca/~ashraf/pubs/sigmod10multidom.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.433.1404","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.433.1404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://cs.uwaterloo.ca/~ashraf/theses/MahmoudMMath10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W95524657","https://openalex.org/W203696055","https://openalex.org/W291262356","https://openalex.org/W343945789","https://openalex.org/W938539187","https://openalex.org/W1490760466","https://openalex.org/W1504694836","https://openalex.org/W1565377632","https://openalex.org/W1646278814","https://openalex.org/W1673310716","https://openalex.org/W1938740620","https://openalex.org/W1968832971","https://openalex.org/W1969831559","https://openalex.org/W1990061958","https://openalex.org/W2008896880","https://openalex.org/W2059268928","https://openalex.org/W2066680326","https://openalex.org/W2108489852","https://openalex.org/W2113076747","https://openalex.org/W2125055259","https://openalex.org/W2127218421","https://openalex.org/W2137435551","https://openalex.org/W2148738951","https://openalex.org/W2153508518","https://openalex.org/W2156909104","https://openalex.org/W2160997301","https://openalex.org/W2168714803","https://openalex.org/W2171262729","https://openalex.org/W2322002063","https://openalex.org/W2482589566","https://openalex.org/W2610179052","https://openalex.org/W2799061466","https://openalex.org/W2912565176","https://openalex.org/W2999729612","https://openalex.org/W4244494905","https://openalex.org/W6603836881","https://openalex.org/W6633894697","https://openalex.org/W7014191107"],"related_works":["https://openalex.org/W629399385","https://openalex.org/W2406112091","https://openalex.org/W4248994601","https://openalex.org/W2125859764","https://openalex.org/W2766698234","https://openalex.org/W2136489971","https://openalex.org/W1128683088","https://openalex.org/W2243208152","https://openalex.org/W1574719525","https://openalex.org/W180239526"],"abstract_inverted_index":{"A":[0,54],"data":[1,11,19,31,44,63,70,103],"integration":[2,25,45,64,71,104],"system":[3,72,92],"offers":[4],"a":[5,48,59,182,188,194,196],"single":[6],"interface":[7],"to":[8,39,66,84,115,117,128,179,203],"multiple":[9],"structured":[10,18,30],"sources.":[12,32],"Many":[13],"application":[14],"contexts":[15],"(e.g.,":[16],"searching":[17],"on":[20,162],"the":[21,24,85,91,111,118,138,163,168,199,209],"web)":[22],"involve":[23],"of":[26,29,140,165,211],"large":[27],"numbers":[28],"At":[33,122],"web":[34,123],"scale,":[35,124],"it":[36,94,125],"is":[37,51,126],"impractical":[38,127],"use":[40],"manual":[41],"or":[42,134],"semi-automatic":[43],"methods,":[46],"so":[47],"pay-as-you-go":[49,55],"approach":[50,56,149,172],"more":[52],"appropriate.":[53],"entails":[57],"using":[58,181],"fully":[60],"automatic":[61,101],"approximate":[62,102],"technique":[65],"provide":[67],"an":[68,74,148],"initial":[69,75,79],"(i.e.,":[73],"mediated":[76,86],"schema,":[77],"and":[78,88,159,215],"mappings":[80],"from":[81],"source":[82],"schemas":[83,112,130,152,178],"schema),":[87],"then":[89],"refining":[90],"as":[93],"gets":[95],"used.":[96],"Previous":[97],"research":[98],"has":[99],"investigated":[100],"techniques,":[105],"but":[106],"all":[107],"existing":[108],"techniques":[109],"require":[110],"being":[113],"integrated":[114],"belong":[116],"same":[119],"conceptual":[120],"domain.":[121],"classify":[129],"into":[131,153],"domains":[132,154,180,202],"manually":[133],"semi-automatically,":[135],"which":[136],"limits":[137],"applicability":[139],"these":[141],"techniques.":[142,218],"In":[143],"this":[144,204],"paper,":[145],"we":[146],"present":[147],"for":[150,193],"clustering":[151,171,214],"without":[155],"any":[156],"human":[157],"intervention":[158],"based":[160],"only":[161],"names":[164],"attributes":[166],"in":[167,176],"schemas.":[169],"Our":[170],"deals":[173],"with":[174],"uncertainty":[175],"assigning":[177],"probabilistic":[183],"model.":[184],"We":[185,206],"also":[186],"propose":[187],"query":[189,216],"classifier":[190],"that":[191],"determines,":[192],"given":[195],"keyword":[197],"query,":[198],"most":[200],"relevant":[201],"query.":[205],"experimentally":[207],"demonstrate":[208],"effectiveness":[210],"our":[212],"schema":[213],"classification":[217]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}