{"id":"https://openalex.org/W2032871318","doi":"https://doi.org/10.1145/1316902.1316922","title":"Web based linkage","display_name":"Web based linkage","publication_year":2007,"publication_date":"2007-11-09","ids":{"openalex":"https://openalex.org/W2032871318","doi":"https://doi.org/10.1145/1316902.1316922","mag":"2032871318"},"language":"en","primary_location":{"id":"doi:10.1145/1316902.1316922","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1316902.1316922","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 annual ACM international workshop on Web information and data management","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/A5000996063","display_name":"Ergin Elmacioglu","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ergin Elmacioglu","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA","THE PENNSYLVANIA STATE UNIVERSITY, UNIVERSITY PARK, PA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"THE PENNSYLVANIA STATE UNIVERSITY, UNIVERSITY PARK, PA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066305082","display_name":"Min\u2010Yen Kan","orcid":"https://orcid.org/0000-0001-8507-3716"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Min-Yen Kan","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405086","display_name":"Dongwon Lee","orcid":"https://orcid.org/0000-0001-8371-7629"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongwon Lee","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA","THE PENNSYLVANIA STATE UNIVERSITY, UNIVERSITY PARK, PA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"THE PENNSYLVANIA STATE UNIVERSITY, UNIVERSITY PARK, PA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100388333","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0003-4299-1511"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["University of California, Santa Cruz, CA","University of California, Santa Cruz, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Cruz, CA","institution_ids":["https://openalex.org/I185103710"]},{"raw_affiliation_string":"University of California, Santa Cruz, CA#TAB#","institution_ids":["https://openalex.org/I185103710"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5000996063"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":3.4233,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.9224171,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"121","last_page":"128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9902999997138977,"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":0.9679999947547913,"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":0.8091669082641602},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.6970437169075012},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6225115060806274},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5842252969741821},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.49214309453964233},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.4597170352935791},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.45319944620132446},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.45242229104042053},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.4417656660079956},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4142466187477112},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17283710837364197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8091669082641602},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.6970437169075012},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6225115060806274},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5842252969741821},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.49214309453964233},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.4597170352935791},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.45319944620132446},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.45242229104042053},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.4417656660079956},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4142466187477112},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17283710837364197},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1316902.1316922","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1316902.1316922","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 annual ACM international workshop on Web information and data management","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/40961","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/40961","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W130948412","https://openalex.org/W1506138338","https://openalex.org/W1547705211","https://openalex.org/W1559390933","https://openalex.org/W1567365482","https://openalex.org/W1633771733","https://openalex.org/W1646278814","https://openalex.org/W1742677423","https://openalex.org/W1880262756","https://openalex.org/W1956559956","https://openalex.org/W1981825277","https://openalex.org/W1982678692","https://openalex.org/W1991885012","https://openalex.org/W2024770506","https://openalex.org/W2036216970","https://openalex.org/W2046020929","https://openalex.org/W2055405704","https://openalex.org/W2059035258","https://openalex.org/W2067566391","https://openalex.org/W2073471108","https://openalex.org/W2105423800","https://openalex.org/W2106300185","https://openalex.org/W2116544254","https://openalex.org/W2116690618","https://openalex.org/W2122683551","https://openalex.org/W2123561513","https://openalex.org/W2130610812","https://openalex.org/W2135223301","https://openalex.org/W2149393279","https://openalex.org/W2154498027","https://openalex.org/W2159481891","https://openalex.org/W2162337786","https://openalex.org/W2163780445","https://openalex.org/W2165186823","https://openalex.org/W2561675875","https://openalex.org/W2999905431","https://openalex.org/W3087838514","https://openalex.org/W6634133269","https://openalex.org/W6636702202","https://openalex.org/W6637772234","https://openalex.org/W6639619044","https://openalex.org/W6640862754","https://openalex.org/W6677894765","https://openalex.org/W6683373780","https://openalex.org/W6783676914"],"related_works":["https://openalex.org/W2487032012","https://openalex.org/W2211355040","https://openalex.org/W2808916796","https://openalex.org/W2176311362","https://openalex.org/W3012491082","https://openalex.org/W3211905090","https://openalex.org/W1936317645","https://openalex.org/W4310568775","https://openalex.org/W2178148352","https://openalex.org/W2606460416"],"abstract_inverted_index":{"When":[0],"a":[1,38,65,160],"variety":[2],"of":[3,14,54,67,104,114,131],"names":[4],"are":[5],"used":[6],"for":[7,139],"the":[8,12,23,43,46,81,91,99,105,111,129,133,136,140],"same":[9],"real-world":[10],"entity,":[11],"problem":[13,142],"detecting":[15],"all":[16],"such":[17],"variants":[18],"has":[19],"been":[20],"known":[21],"as":[22,45,135],"(record)":[24],"linkage":[25,141],"or":[26,102],"entity":[27,62,69],"resolution":[28],"problem.":[29],"In":[30],"this":[31,34],"paper,":[32],"toward":[33],"problem,":[35],"we":[36,97],"propose":[37],"novel":[39],"approach":[40],"that":[41,59,120],"uses":[42],"Web":[44,134],"collective":[47],"knowledge":[48],"source":[49,138],"in":[50,124,156],"addition":[51],"to":[52,109,159],"contents":[53,103],"entities.":[55],"Our":[56,145],"hypothesis":[57,122],"is":[58,64,143],"if":[60,72],"an":[61,115],"e1":[63,73],"duplicate":[66],"another":[68],"e2,":[70],"and":[71,128,151],"frequently":[74,87],"appears":[75],"together":[76],"with":[77,88],"information":[78,112],"I":[79,89,113],"on":[80,90],"Web,":[82],"then":[83],"e2":[84],"may":[85],"appear":[86],"Web.":[92],"By":[93],"using":[94,132],"search":[95],"engines,":[96],"analyze":[98],"frequency,":[100],"URLs,":[101],"returned":[106],"web":[107],"pages":[108],"capture":[110],"entity.":[116],"Extensive":[117],"experiments":[118],"verify":[119],"our":[121],"holds":[123],"many":[125],"real":[126],"settings,":[127],"idea":[130],"additional":[137],"promising.":[144],"proposal":[146],"shows":[147],"51%":[148],"(on":[149],"average)":[150],"193%":[152],"(at":[153],"best)":[154],"improvement":[155],"precision/recall":[157],"compared":[158],"baseline":[161],"approach.":[162]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
