{"id":"https://openalex.org/W2117058208","doi":"https://doi.org/10.1145/1007568.1007582","title":"An interactive clustering-based approach to integrating source query interfaces on the deep Web","display_name":"An interactive clustering-based approach to integrating source query interfaces on the deep Web","publication_year":2004,"publication_date":"2004-06-13","ids":{"openalex":"https://openalex.org/W2117058208","doi":"https://doi.org/10.1145/1007568.1007582","mag":"2117058208"},"language":"en","primary_location":{"id":"doi:10.1145/1007568.1007582","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1007568.1007582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 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/A5061069727","display_name":"Wensheng Wu","orcid":"https://orcid.org/0000-0002-2948-9773"},"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":"Wensheng Wu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign","University of Illinois at Urbana Champaign"],"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/A5109181755","display_name":"Clement Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Clement Yu","raw_affiliation_strings":["University of Illinois at Chicago"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110256670","display_name":"AnHai Doan","orcid":null},"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":"AnHai Doan","raw_affiliation_strings":["University of Illinois at Urbana-Champaign","University of Illinois at Urbana Champaign"],"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/A5101960531","display_name":"Weiyi Meng","orcid":"https://orcid.org/0000-0002-7246-2058"},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiyi Meng","raw_affiliation_strings":["SUNY at Binghamton"],"affiliations":[{"raw_affiliation_string":"SUNY at Binghamton","institution_ids":["https://openalex.org/I123946342"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061069727"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":56.5231,"has_fulltext":false,"cited_by_count":275,"citation_normalized_percentile":{"value":0.99857494,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"95","last_page":"106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9991999864578247,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9980000257492065,"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":0.8034499883651733},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6472011804580688},{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.5342015027999878},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.427262544631958},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3668127655982971},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3390231728553772},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24758994579315186},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.19269949197769165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8034499883651733},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6472011804580688},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.5342015027999878},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.427262544631958},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3668127655982971},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3390231728553772},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24758994579315186},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.19269949197769165}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1007568.1007582","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1007568.1007582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.526.1058","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.526.1058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uiuc.edu/class/fa05/cs591han/sigmodpods04/sigmod/pdf/R-442.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.89.3036","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.89.3036","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.binghamton.edu/~meng/pub.d/sigmod04-final.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W122885654","https://openalex.org/W140130170","https://openalex.org/W1493454437","https://openalex.org/W1494640588","https://openalex.org/W1545169732","https://openalex.org/W1545344782","https://openalex.org/W1555882878","https://openalex.org/W1556076816","https://openalex.org/W1659541576","https://openalex.org/W1956559956","https://openalex.org/W1987869189","https://openalex.org/W2008896880","https://openalex.org/W2016758618","https://openalex.org/W2052581258","https://openalex.org/W2067566391","https://openalex.org/W2098162425","https://openalex.org/W2106895292","https://openalex.org/W2108489852","https://openalex.org/W2132610455","https://openalex.org/W2138745488","https://openalex.org/W2139135093","https://openalex.org/W2150365753","https://openalex.org/W2156543375","https://openalex.org/W2157060173","https://openalex.org/W2170188121","https://openalex.org/W2170902582","https://openalex.org/W2999729612","https://openalex.org/W4235505822","https://openalex.org/W6605070434","https://openalex.org/W6633446409","https://openalex.org/W6636986008","https://openalex.org/W6640862754","https://openalex.org/W6674809819","https://openalex.org/W6678605463","https://openalex.org/W6680506379","https://openalex.org/W6685116542","https://openalex.org/W6738852829","https://openalex.org/W6822831480"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2037906003","https://openalex.org/W4378699829","https://openalex.org/W2953265498","https://openalex.org/W2533455610","https://openalex.org/W2804364458","https://openalex.org/W4248236804","https://openalex.org/W2910532728","https://openalex.org/W1551575434","https://openalex.org/W4300526709"],"abstract_inverted_index":{"An":[0],"increasing":[1],"number":[2],"of":[3,25,46,53,65,75,99,105,158,167,170,202,207],"data":[4],"sources":[5,32],"now":[6],"become":[7],"available":[8],"on":[9,61],"the":[10,44,51,62,66,70,73,108,114,121,186,191,199,205],"Web,":[11],"but":[12],"often":[13,28,137],"their":[14,54],"contents":[15],"are":[16,85,172,177,212],"only":[17,101],"accessible":[18],"through":[19],"query":[20,55,76,153],"interfaces.":[21,56,71,154],"For":[22],"a":[23,117],"domain":[24],"interest,":[26],"there":[27],"exist":[29],"many":[30],"such":[31],"with":[33,94,162],"varied":[34],"coverage":[35],"or":[36],"querying":[37],"capabilities.":[38],"As":[39],"an":[40,147],"important":[41],"step":[42,64],"to":[43,125,151,179,198],"integration":[45,52,74,115],"these":[47,182],"sources,":[48],"we":[49,59,145],"consider":[50,102],"More":[57],"specifically,":[58],"focus":[60],"crucial":[63],"integration:":[67],"accurately":[68],"matching":[69,152],"While":[72],"interfaces":[77,93,159],"has":[78,124],"received":[79],"more":[80],"attentions":[81],"recently,":[82],"current":[83],"approaches":[84,176,197],"not":[86],"sufficiently":[87],"general:":[88],"(a)":[89],"they":[90,111,136],"all":[91,112],"model":[92],"flat":[95],"schemas;":[96],"(b)":[97],"most":[98],"them":[100],"1:1":[103],"mappings":[104,169],"fields":[106,171],"over":[107],"interfaces;":[109],"(c)":[110],"perform":[113],"in":[116,190],"blackbox-like":[118],"fashion":[119],"and":[120,134,174,193,204,214],"whole":[122],"process":[123],"be":[126],"restarted":[127],"from":[128],"scratch":[129],"if":[130],"anything":[131],"goes":[132],"wrong;":[133],"(d)":[135],"require":[138],"laborious":[139],"parameter":[140],"tuning.":[141],"In":[142],"this":[143],"paper,":[144],"propose":[146,194],"interactive,":[148],"clustering-based":[149],"approach":[150,219],"The":[155],"hierarchical":[156],"nature":[157],"is":[160,220],"captured":[161],"ordered":[163],"trees.":[164],"Varied":[165],"types":[166],"complex":[168],"examined":[173],"several":[175,195],"proposed":[178],"effectively":[180],"identify":[181],"mappings.":[183,209],"We":[184],"put":[185],"human":[187],"integrator":[188],"back":[189],"loop":[192],"novel":[196],"interactive":[200],"learning":[201],"parameters":[203],"resolution":[206],"uncertain":[208],"Extensive":[210],"experiments":[211],"conducted":[213],"results":[215],"show":[216],"that":[217],"our":[218],"highly":[221],"effective.":[222]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":19}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
