{"id":"https://openalex.org/W1968832971","doi":"https://doi.org/10.1145/1031171.1031178","title":"Organizing structured web sources by query schemas","display_name":"Organizing structured web sources by query schemas","publication_year":2004,"publication_date":"2004-11-13","ids":{"openalex":"https://openalex.org/W1968832971","doi":"https://doi.org/10.1145/1031171.1031178","mag":"1968832971"},"language":"en","primary_location":{"id":"doi:10.1145/1031171.1031178","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1031171.1031178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the thirteenth ACM international conference on Information and knowledge management","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, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, IL","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401500","display_name":"Tao Tao","orcid":"https://orcid.org/0000-0002-5630-2070"},"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":"Tao Tao","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, 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, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, 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":3.0872,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":{"value":0.92363216,"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":"22","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9958000183105469,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9958000183105469,"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":0.9952999949455261,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9916999936103821,"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/computer-science","display_name":"Computer science","score":0.7860020399093628},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.6127259135246277},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5867175459861755},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.5735909342765808},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5163537263870239},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4972675144672394},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.490548312664032},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.4256947636604309},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41425493359565735},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.41269150376319885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20960253477096558},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13278478384017944},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.11028972268104553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860020399093628},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.6127259135246277},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5867175459861755},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.5735909342765808},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5163537263870239},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4972675144672394},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.490548312664032},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.4256947636604309},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41425493359565735},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.41269150376319885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20960253477096558},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13278478384017944},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.11028972268104553}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1031171.1031178","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1031171.1031178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the thirteenth ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.75,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W178169250","https://openalex.org/W1501500081","https://openalex.org/W1521439890","https://openalex.org/W1586806958","https://openalex.org/W1879587332","https://openalex.org/W1969831559","https://openalex.org/W1971784203","https://openalex.org/W1988413436","https://openalex.org/W1992419399","https://openalex.org/W2002374079","https://openalex.org/W2027780984","https://openalex.org/W2041674806","https://openalex.org/W2052621018","https://openalex.org/W2057712948","https://openalex.org/W2064686951","https://openalex.org/W2072881690","https://openalex.org/W2076983043","https://openalex.org/W2082503527","https://openalex.org/W2082583687","https://openalex.org/W2093390569","https://openalex.org/W2100958137","https://openalex.org/W2108489852","https://openalex.org/W2112719612","https://openalex.org/W2122943553","https://openalex.org/W2123853152","https://openalex.org/W2125969310","https://openalex.org/W2126004201","https://openalex.org/W2131006463","https://openalex.org/W2137845970","https://openalex.org/W2167403283","https://openalex.org/W2169044456","https://openalex.org/W2221553715","https://openalex.org/W2252034896","https://openalex.org/W2319660501","https://openalex.org/W2756666283","https://openalex.org/W2952277155","https://openalex.org/W4206765718","https://openalex.org/W4247346926","https://openalex.org/W6629971530","https://openalex.org/W6631328736","https://openalex.org/W6678605463","https://openalex.org/W6684703521","https://openalex.org/W6738852829","https://openalex.org/W6770641979","https://openalex.org/W6902931378","https://openalex.org/W7057317600"],"related_works":["https://openalex.org/W2096359267","https://openalex.org/W2026738364","https://openalex.org/W1793997780","https://openalex.org/W2901901036","https://openalex.org/W2013069866","https://openalex.org/W2041106684","https://openalex.org/W2538384344","https://openalex.org/W8514837","https://openalex.org/W2572349046","https://openalex.org/W3125756434"],"abstract_inverted_index":{"In":[0,80],"the":[1,4,11,42,46,70,94,100,114,158,177,191],"recent":[2],"years,":[3],"Web":[5,50,57,174],"has":[6],"been":[7],"rapidly":[8],"\"deepened\"":[9],"with":[10,190],"prevalence":[12],"of":[13,41,48,69,89,96,102,152],"databases":[14],"online.":[15],"On":[16],"this":[17],"deep":[18],"Web,":[19],"many":[20],"sources":[21,34,71,154,163],"are":[22,66,111],"<i>structured</i>":[23],"by":[24,82,113,126,164],"providing":[25],"structured":[26,33,56],"query":[27,59,64,84,175],"interfaces":[28],"and":[29,72,170,187],"results.":[30],"Organizing":[31],"such":[32,127,183],"into":[35,99],"a":[36,87,132],"domain":[37],"hierarchy":[38],"is":[39],"one":[40],"critical":[43],"steps":[44],"toward":[45],"integration":[47],"heterogeneous":[49],"sources.":[51],"We":[52],"observe":[53],"that,":[54],"for":[55,77,119],"sources,":[58],"schemas":[60,85],"<i>ie</i>,":[61],"attributes":[62],"in":[63],"interfaces)":[65],"discriminative":[67],"representatives":[68],"thus":[73],"can":[74],"be":[75],"exploited":[76],"source":[78,97],"characterization.":[79],"particular,":[81],"viewing":[83],"as":[86,184],"type":[88],"categorical":[90,103],"data,":[91],"we":[92,130],"abstract":[93],"problem":[95],"organization":[98],"clustering":[101,160,173,194],"data.":[104],"Our":[105,148],"approach":[106],"hypothesizes":[107],"that":[108,156],"\"homogeneous":[109],"sources\"":[110],"characterized":[112],"same":[115],"hidden":[116],"generative":[117],"models":[118],"their":[120],"schemas.":[121],"To":[122],"find":[123],"clusters":[124],"governed":[125],"statistical":[128,144],"distributions,":[129],"propose":[131],"new":[133],"objective":[134],"function,":[135],"<i>model-differentiation</i>,":[136],"which":[137],"employs":[138],"principled":[139],"hypothesis":[140],"testing":[141],"to":[142],"maximize":[143],"heterogeneity":[145],"among":[146],"clusters.":[147],"evaluation":[149],"over":[150],"hundreds":[151],"real":[153],"indicates":[155],"(1)":[157],"schema-based":[159],"accurately":[161],"organizes":[162],"object":[165],"domains":[166],"<i>eg</i>,":[167],"Books,":[168],"Movies),":[169],"(2)":[171],"on":[172],"schemas,":[176],"model-differentiation":[178],"function":[179],"outperforms":[180],"existing":[181],"ones,":[182],"likelihood,":[185],"entropy,":[186],"context":[188],"linkages,":[189],"hierarchical":[192],"agglomerative":[193],"algorithm.":[195]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":7}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}