{"id":"https://openalex.org/W2000586413","doi":"https://doi.org/10.1145/1046456.1046465","title":"Mining semantics for large scale integration on the web","display_name":"Mining semantics for large scale integration on the web","publication_year":2004,"publication_date":"2004-12-01","ids":{"openalex":"https://openalex.org/W2000586413","doi":"https://doi.org/10.1145/1046456.1046465","mag":"2000586413"},"language":"en","primary_location":{"id":"doi:10.1145/1046456.1046465","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1046456.1046465","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"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 SIGKDD Explorations Newsletter","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/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":"middle","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":"last","author":{"id":"https://openalex.org/A5103037437","display_name":"Zhen Zhang","orcid":"https://orcid.org/0000-0002-6006-7157"},"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":"Zhen Zhang","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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":1.6095,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.89169362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"6","issue":"2","first_page":"67","last_page":"76"},"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/T11719","display_name":"Data Quality and Management","score":0.9983000159263611,"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":0.9977999925613403,"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":0.8496303558349609},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.669528603553772},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.44251134991645813},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.4121294617652893},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4031337797641754},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3837921917438507},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3291330933570862},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.21499675512313843},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11231052875518799}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8496303558349609},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.669528603553772},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.44251134991645813},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.4121294617652893},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4031337797641754},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3837921917438507},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3291330933570862},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.21499675512313843},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11231052875518799}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1046456.1046465","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1046456.1046465","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"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 SIGKDD Explorations Newsletter","raw_type":"journal-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/W291262356","https://openalex.org/W1526001307","https://openalex.org/W1545169732","https://openalex.org/W1879587332","https://openalex.org/W1969831559","https://openalex.org/W2008896880","https://openalex.org/W2027780984","https://openalex.org/W2072881690","https://openalex.org/W2108267498","https://openalex.org/W2108489852","https://openalex.org/W2111606934","https://openalex.org/W2112719612","https://openalex.org/W2117058208","https://openalex.org/W2123853152","https://openalex.org/W2125969310","https://openalex.org/W2126004201","https://openalex.org/W2139135093","https://openalex.org/W2150365753","https://openalex.org/W2162294668","https://openalex.org/W6678605463","https://openalex.org/W6680506379"],"related_works":["https://openalex.org/W4213212078","https://openalex.org/W2112788825","https://openalex.org/W2187227032","https://openalex.org/W1963735073","https://openalex.org/W4233129888","https://openalex.org/W106707639","https://openalex.org/W2146247781","https://openalex.org/W2126703991","https://openalex.org/W2610897791","https://openalex.org/W3153302240"],"abstract_inverted_index":{"The":[0],"Web":[1],"has":[2],"been":[3],"rapidly":[4],"\"deepened\"":[5],"--":[6],"with":[7,53],"myriad":[8],"searchable":[9],"databases":[10],"online,":[11],"where":[12],"data":[13],"are":[14,28],"hidden":[15,98,155],"behind":[16],"query":[17,134],"interfaces.":[18],"Toward":[19],"large":[20,40,76,150,207],"scale":[21,41,77,151,208],"integration":[22,42,152],"over":[23,100],"this":[24,65],"\"deep":[25],"Web,\"":[26],"we":[27,49,115,140,169,191],"facing":[29],"a":[30,81,202],"new":[31],"challenge-":[32],"With":[33],"its":[34,173],"dynamic":[35,44,176],"and":[36,133],"ad-hoc":[37],"nature,":[38],"such":[39,166],"mandates":[43],"semantics":[45,111,148,177,199],"discovery.":[46,112,178],"That":[47],"is,":[48],"must":[50],"on-the-fly":[51],"cope":[52],"\"semantics\"":[54,89],"of":[55,146,165],"dynamically":[56],"discovered":[57],"sources":[58],"without":[59],"pre-configured":[60],"source-specific":[61],"knowledge.":[62],"To":[63],"tackle":[64],"challenge,":[66],"our":[67,117,143,180,193],"initial":[68,121,181],"works":[69,182],"hinge":[70],"on":[71],"the":[72,75,87,125,163],"insight":[73],"that":[74,86],"is":[78,201],"itself":[79],"also":[80],"unique":[82],"opportunity:":[83],"We":[84],"observe":[85],"desired":[88],"often":[90],"connects":[91],"to":[92,161],"surface":[93],"presentation":[94],"characteristics,":[95],"through":[96],"some":[97],"regularities":[99,104,156],"many":[101],"sources.":[102,159],"Such":[103],"can":[105],"be":[106],"essentially":[107],"leveraged":[108],"in":[109,119],"enabling":[110,206],"In":[113],"particular,":[114],"report":[116],"evidences":[118],"three":[120],"tasks":[122],"for":[123,149,175,198],"integrating":[124],"deep":[126],"Web:":[127],"interface":[128],"extraction,":[129],"schema":[130],"matching":[131],",":[132],"translation.":[135],"Generalizing":[136],"these":[137],"specific":[138],"evidences,":[139],"thus":[141],"propose":[142],"\"unified":[144],"insight\"":[145],"\"mining\"":[147],"by":[153],"exploiting":[154],"across":[157],"holistic":[158,167,196],"Further,":[160],"fulfill":[162],"promise":[164],"mining,":[168],"discuss":[170],"challenges":[171],"toward":[172,205],"realization":[174],"As":[179],"as":[183,185],"well":[184],"several":[186],"related":[187],"efforts":[188],"have":[189],"witnessed,":[190],"believe":[192],"unified":[194],"insight,":[195],"mining":[197],"discovery,":[200],"promising":[203],"methodology":[204],"integration.":[209]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}