{"id":"https://openalex.org/W1981578383","doi":"https://doi.org/10.14778/2536336.2536345","title":"Discovering linkage points over web data","display_name":"Discovering linkage points over web data","publication_year":2013,"publication_date":"2013-04-01","ids":{"openalex":"https://openalex.org/W1981578383","doi":"https://doi.org/10.14778/2536336.2536345","mag":"1981578383"},"language":"en","primary_location":{"id":"doi:10.14778/2536336.2536345","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2536336.2536345","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","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/A5068065546","display_name":"Oktie Hassanzadeh","orcid":"https://orcid.org/0000-0001-5307-9857"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Oktie Hassanzadeh","raw_affiliation_strings":["IBM T.J. Watson Research Center","IBM T.J. Watson research Center"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center","institution_ids":[]},{"raw_affiliation_string":"IBM T.J. Watson research Center","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108778575","display_name":"Ken Q. Pu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119257","display_name":"University of Information Technology and Communications","ror":"https://ror.org/028h0pd91","country_code":"IQ","type":"education","lineage":["https://openalex.org/I4210119257"]}],"countries":["IQ"],"is_corresponding":false,"raw_author_name":"Ken Q. Pu","raw_affiliation_strings":["UOIT","UOIT >  >  >  >"],"affiliations":[{"raw_affiliation_string":"UOIT","institution_ids":["https://openalex.org/I4210119257"]},{"raw_affiliation_string":"UOIT >  >  >  >","institution_ids":["https://openalex.org/I4210119257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087408951","display_name":"Soheil Hassas Yeganeh","orcid":"https://orcid.org/0009-0007-7282-5158"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Soheil Hassas Yeganeh","raw_affiliation_strings":["University of Toronto"],"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022619313","display_name":"Ren\u00e9e J. Miller","orcid":"https://orcid.org/0000-0002-1484-4787"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ren\u00e9e J. Miller","raw_affiliation_strings":["University of Toronto"],"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041152581","display_name":"Lucian Popa","orcid":"https://orcid.org/0000-0002-0659-9144"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lucian Popa","raw_affiliation_strings":["IBM Research-Almaden"],"affiliations":[{"raw_affiliation_string":"IBM Research-Almaden","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110264798","display_name":"Mauricio A. Hern\u00e1ndez","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mauricio A. Hern\u00e1ndez","raw_affiliation_strings":["IBM Research-Almaden"],"affiliations":[{"raw_affiliation_string":"IBM Research-Almaden","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004469222","display_name":"Howard Ho","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Howard Ho","raw_affiliation_strings":["IBM Research-Almaden"],"affiliations":[{"raw_affiliation_string":"IBM Research-Almaden","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5068065546"],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":6.4017,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.96393316,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"6","issue":"6","first_page":"445","last_page":"456"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9995999932289124,"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":0.9995999932289124,"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":0.998199999332428,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.991599977016449,"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":0.8146275281906128},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.7998641729354858},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.7349311113357544},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.6276862621307373},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6041451096534729},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.509086549282074},{"id":"https://openalex.org/keywords/linked-data","display_name":"Linked data","score":0.48449084162712097},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.4314950704574585},{"id":"https://openalex.org/keywords/star-schema","display_name":"Star schema","score":0.4292307496070862},{"id":"https://openalex.org/keywords/database-schema","display_name":"Database schema","score":0.4278259873390198},{"id":"https://openalex.org/keywords/semi-structured-model","display_name":"Semi-structured model","score":0.41371193528175354},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.3358965218067169},{"id":"https://openalex.org/keywords/database-design","display_name":"Database design","score":0.121407151222229}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8146275281906128},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.7998641729354858},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.7349311113357544},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.6276862621307373},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6041451096534729},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.509086549282074},{"id":"https://openalex.org/C69075417","wikidata":"https://www.wikidata.org/wiki/Q515701","display_name":"Linked data","level":3,"score":0.48449084162712097},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.4314950704574585},{"id":"https://openalex.org/C190703929","wikidata":"https://www.wikidata.org/wiki/Q1331138","display_name":"Star schema","level":4,"score":0.4292307496070862},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.4278259873390198},{"id":"https://openalex.org/C56310702","wikidata":"https://www.wikidata.org/wiki/Q2269281","display_name":"Semi-structured model","level":4,"score":0.41371193528175354},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.3358965218067169},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.121407151222229},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/2536336.2536345","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2536336.2536345","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.308.4635","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.4635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.vldb.org/pvldb/vol6/p445-hassanzadeh.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.4399999976158142,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W20290297","https://openalex.org/W1547612978","https://openalex.org/W1556137908","https://openalex.org/W1988674507","https://openalex.org/W1992673035","https://openalex.org/W1995099886","https://openalex.org/W2008896880","https://openalex.org/W2014964486","https://openalex.org/W2021739502","https://openalex.org/W2042389627","https://openalex.org/W2110686900","https://openalex.org/W2112129552","https://openalex.org/W2139021951","https://openalex.org/W2153257312","https://openalex.org/W2155482025","https://openalex.org/W2164625277","https://openalex.org/W2165612380","https://openalex.org/W2293253366","https://openalex.org/W2295240344","https://openalex.org/W2405356156","https://openalex.org/W2407149353","https://openalex.org/W2611894836","https://openalex.org/W3121289605","https://openalex.org/W4252076394","https://openalex.org/W4302802341","https://openalex.org/W6684620663","https://openalex.org/W6737354466"],"related_works":["https://openalex.org/W2092058806","https://openalex.org/W2103472145","https://openalex.org/W2351507151","https://openalex.org/W2139135093","https://openalex.org/W2153512431","https://openalex.org/W2381593392","https://openalex.org/W2376319089","https://openalex.org/W2766698234","https://openalex.org/W945629821","https://openalex.org/W3030019037"],"abstract_inverted_index":{"A":[0],"basic":[1,157],"step":[2,159],"in":[3,54,145,152,211,215],"integration":[4,213],"is":[5,35,96,115],"the":[6,51,55,65,93,113,156,205],"identification":[7,195],"of":[8,45,59,89,175,178,188,196,207],"linkage":[9,168,197],"points,":[10],"i.e.,":[11],"finding":[12],"attributes":[13,44,130],"that":[14,23,42,128],"are":[15],"shared":[16,121],"(or":[17],"related)":[18],"between":[19],"data":[20,63,75,120],"sources,":[21],"and":[22,57,61,85,167,182,185,193],"can":[24,141],"be":[25,104,143],"used":[26],"to":[27,48,109,116],"match":[28,40],"records":[29],"or":[30],"entities":[31],"across":[32],"sources.":[33,124],"This":[34],"usually":[36],"performed":[37],"using":[38],"a":[39,81,161,172,176,186],"operator,":[41],"associates":[43],"one":[46],"database":[47],"another.":[49],"However,":[50],"massive":[52],"growth":[53],"amount":[56],"variety":[58],"unstructured":[60],"semi-structured":[62],"on":[64],"Web":[66,200],"has":[67],"created":[68],"new":[69],"challenges":[70],"for":[71,191],"this":[72,153],"task.":[73],"Such":[74],"sources":[76],"often":[77],"do":[78],"not":[79,97,136],"have":[80],"fixed":[82],"pre-defined":[83],"schema":[84,98,139,165],"contain":[86],"large":[87],"numbers":[88],"diverse":[90],"attributes.":[91],"Furthermore,":[92],"end":[94],"goal":[95,114],"alignment":[99],"as":[100,138],"these":[101,123],"schemas":[102],"may":[103],"too":[105],"heterogeneous":[106],"(and":[107],"dynamic)":[108],"meaningfully":[110],"align.":[111],"Rather,":[112],"align":[117],"any":[118],"overlapping":[119],"by":[122],"We":[125,170,202],"will":[126],"show":[127],"even":[129],"with":[131,160],"different":[132],"meanings":[133],"(that":[134],"would":[135],"qualify":[137],"matches)":[140],"sometimes":[142],"useful":[144],"aligning":[146],"data.":[147,201],"The":[148],"solution":[149],"we":[150],"propose":[151],"paper":[154],"replaces":[155],"schema-matching":[158],"more":[162],"complex":[163],"instance-based":[164],"analysis":[166],"discovery.":[169],"present":[171],"framework":[173],"consisting":[174],"library":[177],"efficient":[179,194],"lexical":[180],"analyzers":[181],"similarity":[183],"functions,":[184],"set":[187],"search":[189],"algorithms":[190,210],"effective":[192],"points":[198],"over":[199],"experimentally":[203],"evaluate":[204],"effectiveness":[206],"our":[208],"proposed":[209],"real-world":[212],"scenarios":[214],"several":[216],"domains.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}