{"id":"https://openalex.org/W2043139552","doi":"https://doi.org/10.1145/1008694.1008696","title":"Mining complex matchings across Web query interfaces","display_name":"Mining complex matchings across Web query interfaces","publication_year":2004,"publication_date":"2004-06-13","ids":{"openalex":"https://openalex.org/W2043139552","doi":"https://doi.org/10.1145/1008694.1008696","mag":"2043139552"},"language":"en","primary_location":{"id":"doi:10.1145/1008694.1008696","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008694.1008696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM SIGMOD workshop on Research issues in data mining and knowledge discovery","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/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","University of Illinois at Urbana Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","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","University of Illinois at Urbana Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019539533","display_name":"Jiawei Han","orcid":"https://orcid.org/0000-0002-3629-2696"},"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":"Jiawei Han","raw_affiliation_strings":["University of Illinois at Urbana-Champaign","University of Illinois at Urbana Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.423,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.91498867,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9986000061035156,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9986000061035156,"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":0.9973999857902527,"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/T11106","display_name":"Data Management and Algorithms","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.82579106092453},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.7029547691345215},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.6805658340454102},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6575742959976196},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.5208114385604858},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.5143269300460815},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.46942904591560364},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.46572205424308777},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4372381567955017},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39548003673553467},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.28819766640663147},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2703532576560974},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.24053218960762024},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09240373969078064}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.82579106092453},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.7029547691345215},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6805658340454102},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6575742959976196},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.5208114385604858},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.5143269300460815},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.46942904591560364},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.46572205424308777},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4372381567955017},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39548003673553467},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.28819766640663147},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2703532576560974},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.24053218960762024},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09240373969078064},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1008694.1008696","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008694.1008696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM SIGMOD workshop on Research issues in data mining and knowledge discovery","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W20214369","https://openalex.org/W1480810164","https://openalex.org/W1586806958","https://openalex.org/W1728974518","https://openalex.org/W1969831559","https://openalex.org/W2008896880","https://openalex.org/W2066277072","https://openalex.org/W2077296695","https://openalex.org/W2089634871","https://openalex.org/W2100417212","https://openalex.org/W2105423800","https://openalex.org/W2108489852","https://openalex.org/W2123853152","https://openalex.org/W2125969310","https://openalex.org/W2139135093","https://openalex.org/W2150365753","https://openalex.org/W2166559705","https://openalex.org/W2210278139","https://openalex.org/W2221553715","https://openalex.org/W6678605463","https://openalex.org/W6680506379"],"related_works":["https://openalex.org/W1528218860","https://openalex.org/W2026738364","https://openalex.org/W2096359267","https://openalex.org/W1997310773","https://openalex.org/W2901901036","https://openalex.org/W2093300859","https://openalex.org/W2330073594","https://openalex.org/W2124814993","https://openalex.org/W3114052401","https://openalex.org/W2163573236"],"abstract_inverted_index":{"To":[0,55],"enable":[1],"information":[2],"integration,":[3],"schema":[4,68],"matching":[5,27,69,77],"is":[6],"a":[7,20,29,62,167],"critical":[8],"step":[9],"for":[10,73],"discovering":[11],"semantic":[12,127],"correspondences":[13],"of":[14,40,76,173,176],"attributes":[15,130,150],"across":[16,120],"heterogeneous":[17],"sourcess.":[18],"As":[19],"new":[21],"attempt,":[22],"this":[23,57,59,90],"paper":[24,60],"studies":[25],"such":[26,125],"as":[28,70],"data":[30],"mining":[31,169,175,204],"problem.":[32],"Specifically,":[33],"while":[34],"complex":[35,44,97,126,164],"matchings":[36,98,165,210],"are":[37,151],"common,":[38],"because":[39,154],"their":[41],"far":[42],"more":[43],"search":[45],"space,":[46],"most":[47],"existing":[48],"techniques":[49],"focus":[50],"on":[51,86,185],"simple":[52],"1:1":[53],"matchings.":[54],"tackle":[56],"challenge,":[58],"takes":[61],"conceptually":[63],"novel":[64],"approach":[65,184,205],"by":[66,166],"viewing":[67],"correlation":[71,168,203],"mining,":[72],"our":[74,183],"task":[75],"Web":[78,187],"query":[79,93,121,141],"interfaces":[80,94,122,142],"to":[81,105,137,162],"integrate":[82],"the":[83,87,111,117,198,202],"myriad":[84],"databases":[85],"Internet.":[88],"On":[89],"\"deep":[91],"Web,\"":[92],"generally":[95],"form":[96],"between":[99],"attribute":[100],"groups":[101],"(e.g.,":[102,131,193],"{author}":[103],"corresponds":[104],"{first":[106,132],"name,":[107,133],"last":[108,134],"name}":[109],"in":[110,140,189],"Books":[112,194],"domain).":[113],"We":[114,181],"observe":[115],"that":[116,201],"co-occurrences":[118],"patterns":[119],"often":[123],"reveal":[124],"relationships:":[128],"grouping":[129],"name})":[135],"tend":[136],"be":[138],"co-present":[139],"and":[143,178,195,197],"thus":[144],"positively":[145],"correlated.":[146],"In":[147],"contrast,":[148],"synonym":[149],"negatively":[152],"correlated":[153],"they":[155],"rarely":[156],"co-occur.":[157],"This":[158],"insight":[159],"enables":[160],"us":[161],"discover":[163,207],"approach,":[170],"which":[171],"consists":[172],"dual":[174],"positive":[177],"negative":[179],"correlations.":[180],"evaluate":[182],"deep":[186],"sources":[188],"several":[190],"object":[191],"domains":[192],"Airfares)":[196],"results":[199],"show":[200],"does":[206],"semantically":[208],"meaningful":[209],"among":[211],"attributes.":[212]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
