{"id":"https://openalex.org/W2118966476","doi":"https://doi.org/10.1145/1132863.1132872","title":"Automatic complex schema matching across Web query interfaces","display_name":"Automatic complex schema matching across Web query interfaces","publication_year":2006,"publication_date":"2006-03-01","ids":{"openalex":"https://openalex.org/W2118966476","doi":"https://doi.org/10.1145/1132863.1132872","mag":"2118966476"},"language":"en","primary_location":{"id":"doi:10.1145/1132863.1132872","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1132863.1132872","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Database Systems","raw_type":"journal-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/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":true,"raw_author_name":"Bin He","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL","[University of Illinois at Urbana-Champaign,Urbana,IL]"],"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]"],"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":2,"corresponding_author_ids":["https://openalex.org/A5101494989"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":18.5339,"has_fulltext":false,"cited_by_count":104,"citation_normalized_percentile":{"value":0.9953004,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"31","issue":"1","first_page":"346","last_page":"395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9977999925613403,"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":0.9977999925613403,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9975000023841858,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9972000122070312,"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":0.8935973644256592},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.8491024971008301},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.6406619548797607},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6303061246871948},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5044091939926147},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.45210808515548706},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4371924102306366},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.4123491942882538},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.3096219301223755},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2326212227344513},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.22959378361701965}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8935973644256592},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.8491024971008301},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6406619548797607},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6303061246871948},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5044091939926147},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.45210808515548706},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4371924102306366},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.4123491942882538},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.3096219301223755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2326212227344513},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.22959378361701965},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1132863.1132872","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1132863.1132872","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Database Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W20214369","https://openalex.org/W291262356","https://openalex.org/W602980269","https://openalex.org/W1534024124","https://openalex.org/W1545169732","https://openalex.org/W1555244713","https://openalex.org/W1600537614","https://openalex.org/W1728974518","https://openalex.org/W1969831559","https://openalex.org/W1988413436","https://openalex.org/W2008896880","https://openalex.org/W2027780984","https://openalex.org/W2051834357","https://openalex.org/W2053539645","https://openalex.org/W2066277072","https://openalex.org/W2089634871","https://openalex.org/W2094930182","https://openalex.org/W2100417212","https://openalex.org/W2105423800","https://openalex.org/W2108489852","https://openalex.org/W2110686900","https://openalex.org/W2114990184","https://openalex.org/W2115947619","https://openalex.org/W2117058208","https://openalex.org/W2123853152","https://openalex.org/W2125969310","https://openalex.org/W2139135093","https://openalex.org/W2140897975","https://openalex.org/W2142385580","https://openalex.org/W2143607396","https://openalex.org/W2150365753","https://openalex.org/W2156543375","https://openalex.org/W2163329495","https://openalex.org/W2166559705","https://openalex.org/W2210278139","https://openalex.org/W2221553715","https://openalex.org/W2302382203","https://openalex.org/W2318031348","https://openalex.org/W2798170591","https://openalex.org/W2912934387","https://openalex.org/W4237841550","https://openalex.org/W6600772290","https://openalex.org/W6633385888","https://openalex.org/W6815619692","https://openalex.org/W7057317600"],"related_works":["https://openalex.org/W3208717180","https://openalex.org/W2406112091","https://openalex.org/W2125859764","https://openalex.org/W1128683088","https://openalex.org/W2372910313","https://openalex.org/W3138074544","https://openalex.org/W2036644834","https://openalex.org/W4310041472","https://openalex.org/W2408969024","https://openalex.org/W2016611314"],"abstract_inverted_index":{"To":[0,40,240],"enable":[1],"information":[2],"integration,":[3],"schema":[4,53,268,316],"matching":[5,54,63,180,207,238,308],"is":[6],"a":[7,47,154,254,283],"critical":[8],"step":[9],"for":[10,59,198,213],"discovering":[11,199],"semantic":[12,114],"correspondences":[13],"of":[14,25,62,167,173,262,290,293,333],"attributes":[15,117,137],"across":[16,107],"heterogeneous":[17],"sources.":[18],"While":[19],"complex":[20,29,84,113,151,200],"matchings":[21,85,152,334],"are":[22,138],"common,":[23],"because":[24,141],"their":[26,275],"far":[27],"more":[28],"search":[30],"space,":[31],"most":[32],"existing":[33],"techniques":[34,212],"focus":[35],"on":[36,72,188,220],"simple":[37],"1:1":[38],"matchings.":[39,201],"tackle":[41],"this":[42,44,76],"challenge,":[43],"article":[45],"takes":[46],"conceptually":[48],"novel":[49,255],"approach":[50],"by":[51,153,265,278],"viewing":[52],"as":[55],"correlation":[56,155],"mining":[57,156,172],",":[58,170],"our":[60,298],"task":[61],"Web":[64,78,335],"query":[65,80,108,128,336],"interfaces":[66,81,109,129,191],"to":[67,92,124,149,203],"integrate":[68,251],"the":[69,73,98,104,162,185,193,205,217,227,237,242,267,291,294,302,307,320,324],"myriad":[70],"databases":[71],"Internet.":[74],"On":[75],"\u201cdeep":[77],"\u201d":[79],"generally":[82],"form":[83],"between":[86],"attribute":[87],"groups":[88],"(e.g.,":[89,118],"{author}":[90],"corresponds":[91],"{first":[93,119],"name,":[94,120],"last":[95,121],"name}":[96],"in":[97,127,230],"Books":[99],"domain).":[100],"We":[101,183],"observe":[102],"that":[103,226,301],"co-occurrences":[105],"patterns":[106],"often":[110],"reveal":[111],"such":[112,247],"relationships:":[115],"grouping":[116],"name})":[122],"tend":[123],"be":[125],"co-present":[126],"and":[130,175,178,192,273,313],"thus":[131,314,328],"positively":[132],"correlated.":[133],"In":[134,158],"contrast,":[135],"synonym":[136],"negatively":[139],"correlated":[140],"they":[142],"rarely":[143],"co-occur.":[144],"This":[145],"insight":[146],"enables":[147],"us":[148],"discover":[150],"approach.":[157,296],"particular,":[159],"we":[160,209,224,250,286,327],"develop":[161],"DCM":[163,186,218,243,263,321],"framework,":[164],"which":[165,258],"consists":[166],"data":[168,269],"preprocessing":[169],"dual":[171],"positive":[174],"negative":[176],"correlations,":[177],"finally":[179],"construction":[181],".":[182],"evaluate":[184],"framework":[187,219,244,322],"manually":[189],"extracted":[190,222,312],"results":[194,277],"show":[195,300],"good":[196],"accuracy":[197],"Further,":[202],"automate":[204],"entire":[206],"process,":[208],"incorporate":[210],"automatic":[211,231,331],"interface":[214,232],"extraction.":[215],"Executing":[216],"automatically":[221,311],"interfaces,":[223],"find":[225],"inevitable":[228],"errors":[229],"extraction":[233],"may":[234],"significantly":[235,305],"affect":[236],"result.":[239],"make":[241],"robust":[245],"against":[246],"\u201cnoisy\u201d":[248],"schemas,":[249],"it":[252],"with":[253,323],"\u201censemble\u201d":[256],"approach,":[257,326],"creates":[259],"an":[260,330],"ensemble":[261,295,325],"matchers,":[264],"randomizing":[266],"into":[270],"many":[271],"trials":[272],"aggregating":[274],"ranked":[276],"taking":[279],"majority":[280],"voting.":[281],"As":[282],"principled":[284],"basis,":[285],"provide":[287],"analytic":[288],"justification":[289],"robustness":[292],"Empirically,":[297],"experiments":[299],"\u201censemblization\u201d":[303],"indeed":[304],"boosts":[306],"accuracy,":[309],"over":[310],"noisy":[315],"data.":[317],"By":[318],"employing":[319],"complete":[329],"process":[332],"interfaces.":[337]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}