{"id":"https://openalex.org/W2053539645","doi":"https://doi.org/10.1145/1081870.1081920","title":"Making holistic schema matching robust","display_name":"Making holistic schema matching robust","publication_year":2005,"publication_date":"2005-08-21","ids":{"openalex":"https://openalex.org/W2053539645","doi":"https://doi.org/10.1145/1081870.1081920","mag":"2053539645"},"language":"en","primary_location":{"id":"doi:10.1145/1081870.1081920","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101494989","display_name":"Bin He","orcid":"https://orcid.org/0000-0001-7385-5542"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin He","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL","[University of Illinois at Urbana-Champaign,Urbana,IL]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[University of Illinois at Urbana-Champaign,Urbana,IL]","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101880377","display_name":"Kevin Chen\u2013Chuan Chang","orcid":"https://orcid.org/0000-0003-0997-6803"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Chen-Chuan Chang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL","[University of Illinois at Urbana-Champaign,Urbana,IL]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[University of Illinois at Urbana-Champaign,Urbana,IL]","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":3.7513,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.94189251,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"88","issue":null,"first_page":"429","last_page":"438"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9965000152587891,"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/schema-matching","display_name":"Schema matching","score":0.9130102396011353},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8019709587097168},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.7001931667327881},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6687972545623779},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.5627385973930359},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5476388931274414},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.4633655250072479},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.412795752286911},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4106690287590027},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39378929138183594},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36295995116233826}],"concepts":[{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.9130102396011353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8019709587097168},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.7001931667327881},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6687972545623779},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.5627385973930359},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5476388931274414},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.4633655250072479},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.412795752286911},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4106690287590027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39378929138183594},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36295995116233826},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1081870.1081920","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6399999856948853,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W20214369","https://openalex.org/W72943092","https://openalex.org/W336063547","https://openalex.org/W602980269","https://openalex.org/W1545169732","https://openalex.org/W1969831559","https://openalex.org/W2008896880","https://openalex.org/W2027780984","https://openalex.org/W2042389627","https://openalex.org/W2043139552","https://openalex.org/W2089634871","https://openalex.org/W2108489852","https://openalex.org/W2110686900","https://openalex.org/W2114990184","https://openalex.org/W2117058208","https://openalex.org/W2123853152","https://openalex.org/W2125969310","https://openalex.org/W2139135093","https://openalex.org/W2150365753","https://openalex.org/W2155031665","https://openalex.org/W2318031348","https://openalex.org/W2325331228","https://openalex.org/W2912934387","https://openalex.org/W6678605463","https://openalex.org/W6680506379"],"related_works":["https://openalex.org/W1528218860","https://openalex.org/W2406112091","https://openalex.org/W2125859764","https://openalex.org/W1128683088","https://openalex.org/W2372910313","https://openalex.org/W3138074544","https://openalex.org/W4310041472","https://openalex.org/W2938811602","https://openalex.org/W2036644834","https://openalex.org/W2408969024"],"abstract_inverted_index":{"The":[0],"Web":[27],"has":[2,43,79],"been":[3,44],"rapidly":[4],"deepened":[5],"by":[6,58,97,154,165,188],"myriad":[7],"searchable":[8],"databases":[9],"online,":[10],"where":[11],"data":[12,99,169,214],"are":[13],"hidden":[14],"behind":[15],"query":[16,41],"interfaces.":[17],"As":[18,192],"an":[19,161],"essential":[20,129],"task":[21],"toward":[22],"integrating":[23],"these":[24],"massive":[25],"deep":[26],"sources,":[28],"large":[29,85,117],"scale":[30,118],"schema":[31,77,111,168,227],"matching":[32,60,78,122,223],"(i.e.,":[33],"discovering":[34],"semantic":[35],"correspondences":[36],"of":[37,87,110,163,200,203,235],"attributes":[38],"across":[39],"many":[40,50,61,171],"interfaces)":[42],"actively":[45],"studied":[46],"recently.":[47],"In":[48],"particular,":[49],"works":[51],"have":[52],"emerged":[53],"to":[54,123,130],"address":[55],"this":[56,139,204],"problem":[57,95],"holistically":[59],"schemas":[62],"at":[63],"the":[64,84,93,107,176,201,217,222,232],"same":[65,177],"time":[66],"and":[67,148,182,229],"thus":[68,128,230],"pursuing":[69],"mining":[70],"approaches":[71],"in":[72,106,116],"nature.":[73],"However,":[74],"while":[75],"holistic":[76,121,237],"built":[80],"its":[81],"promise":[82],"upon":[83],"quantity":[86],"input":[88,167],"schemas,":[89],"it":[90,126,132],"also":[91],"suffers":[92],"robustness":[94,234],"caused":[96],"noisy":[98,135,226],"quality.":[100],"Such":[101],"noises":[102],"often":[103],"inevitably":[104],"arise":[105],"automatic":[108],"extraction":[109],"data,":[112],"which":[113,151],"is":[114,127,152],"mandatory":[115],"integration.":[119],"For":[120],"be":[124],"viable,":[125],"make":[131],"robust":[133],"against":[134],"schemas.":[136],"To":[137],"tackle":[138],"challenge,":[140],"we":[141,196],"propose":[142],"a":[143,193,236],"data-ensemble":[144,205],"framework":[145],"with":[146],"sampling":[147],"voting":[149],"techniques,":[150],"inspired":[153],"bagging":[155],"predictors.":[156],"Specifically,":[157],"our":[158,209],"approach":[159],"creates":[160],"ensemble":[162],"matchers,":[164],"randomizing":[166],"into":[170],"independently":[172],"downsampled":[173],"trials,":[174],"executing":[175],"matcher":[178],"on":[179,211],"each":[180],"trial":[181],"then":[183],"aggregating":[184],"their":[185],"ranked":[186],"results":[187],"taking":[189],"majority":[190],"voting.":[191],"principled":[194],"basis,":[195],"provide":[197],"analytic":[198],"justification":[199],"effectiveness":[202],"framework.":[206],"Further,":[207],"empirically,":[208],"experiments":[210],"real":[212],"show":[215],"that":[216],"ensemblization":[218],"indeed":[219],"significantly":[220],"boosts":[221],"accuracy":[224],"under":[225],"input,":[228],"maintains":[231],"desired":[233],"matcher.":[238]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}