{"id":"https://openalex.org/W2128661986","doi":"https://doi.org/10.1109/wiri.2005.2","title":"A Fast Linkage Detection Scheme for Multi-Source Information Integration","display_name":"A Fast Linkage Detection Scheme for Multi-Source Information Integration","publication_year":2005,"publication_date":"2005-12-13","ids":{"openalex":"https://openalex.org/W2128661986","doi":"https://doi.org/10.1109/wiri.2005.2","mag":"2128661986"},"language":"en","primary_location":{"id":"doi:10.1109/wiri.2005.2","doi":"https://doi.org/10.1109/wiri.2005.2","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wiri.2005.2","pdf_url":null,"source":{"id":"https://openalex.org/S7407115208","display_name":"International Workshop on Challenges in Web Information Retrieval and Integration (WIRI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Workshop on Challenges in Web Information Retrieval and Integration","raw_type":"proceedings-article"},"volume":null,"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/A5041062417","display_name":"Akiko Aizawa","orcid":"https://orcid.org/0000-0001-6544-5076","observed_orcids":["https://orcid.org/0000-0001-6544-5076"]},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"A. Aizawa","raw_affiliation_strings":["National Institute of Informatics, Graduate University of Advanced Studies (SOKENDAI), Tokyo, Japan","National Intsitute of Informatics, The Graduate University for Advanced Studies Hitotsubashi, Chiyoda-ku, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Graduate University of Advanced Studies (SOKENDAI), Tokyo, Japan","institution_ids":["https://openalex.org/I184597095","https://openalex.org/I200475212"]},{"raw_affiliation_string":"National Intsitute of Informatics, The Graduate University for Advanced Studies Hitotsubashi, Chiyoda-ku, Japan#TAB#","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027561196","display_name":"Keizo Oyama","orcid":"https://orcid.org/0000-0003-4385-8798","observed_orcids":["https://orcid.org/0000-0003-4385-8798"]},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Oyama","raw_affiliation_strings":["National Institute of Informatics, Graduate University of Advanced Studies (SOKENDAI), Tokyo, Japan","National Intsitute of Informatics, The Graduate University for Advanced Studies Hitotsubashi, Chiyoda-ku, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Graduate University of Advanced Studies (SOKENDAI), Tokyo, Japan","institution_ids":["https://openalex.org/I184597095","https://openalex.org/I200475212"]},{"raw_affiliation_string":"National Intsitute of Informatics, The Graduate University for Advanced Studies Hitotsubashi, Chiyoda-ku, Japan#TAB#","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2267,"has_fulltext":false,"cited_by_count":83,"citation_normalized_percentile":{"value":0.94692575,"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":"30","last_page":"39"},"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/T14330","display_name":"Library Science and Information Systems","score":0.0,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.0,"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/data-linkage","display_name":"data linkage","score":0.9950000047683716},{"id":"https://openalex.org/keywords/entity-resolution","display_name":"entity resolution","score":0.7689999938011169},{"id":"https://openalex.org/keywords/multi-source-data-fusion","display_name":"multi-source data fusion","score":0.8479999899864197},{"id":"https://openalex.org/keywords/suffix-arrays","display_name":"suffix arrays","score":0.7549999952316284},{"id":"https://openalex.org/keywords/n-grams","display_name":"n-grams","score":0.8130000233650208},{"id":"https://openalex.org/keywords/bibliographic-databases","display_name":"bibliographic databases","score":0.765999972820282},{"id":"https://openalex.org/keywords/large-scale-data","display_name":"large-scale data","score":0.7110000252723694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.804885745048523},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.8011581897735596},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7179203033447266},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.6796699166297913},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5868253111839294},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5456571578979492},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.533370852470398},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.4872802495956421},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.47690629959106445},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.4677557945251465},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.45840030908584595},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34295719861984253},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09504100680351257},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","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},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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:10.1109/wiri.2005.2","doi":"https://doi.org/10.1109/wiri.2005.2","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wiri.2005.2","pdf_url":null,"source":{"id":"https://openalex.org/S7407115208","display_name":"International Workshop on Challenges in Web Information Retrieval and Integration (WIRI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Workshop on Challenges in Web Information Retrieval and Integration","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.76.2305","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.76.2305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.nii.ac.jp/~akiko/papers/wiri2005_aiz.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W25706487","https://openalex.org/W36024057","https://openalex.org/W154872207","https://openalex.org/W1557365335","https://openalex.org/W1569123402","https://openalex.org/W1581262234","https://openalex.org/W1612155886","https://openalex.org/W1920916604","https://openalex.org/W1976541661","https://openalex.org/W1982806687","https://openalex.org/W1999823970","https://openalex.org/W2024770506","https://openalex.org/W2034190452","https://openalex.org/W2036216970","https://openalex.org/W2047965058","https://openalex.org/W2052390074","https://openalex.org/W2063408112","https://openalex.org/W2067566391","https://openalex.org/W2086322024","https://openalex.org/W2111625757","https://openalex.org/W2116544254","https://openalex.org/W2145130412","https://openalex.org/W2152401660","https://openalex.org/W2154711808","https://openalex.org/W2154785834","https://openalex.org/W2161936973","https://openalex.org/W2164456230","https://openalex.org/W2171574281","https://openalex.org/W2334251884","https://openalex.org/W4234053595","https://openalex.org/W4235720003","https://openalex.org/W4254734767"],"related_works":["https://openalex.org/W7100365699","https://openalex.org/W2528898284","https://openalex.org/W2055405704","https://openalex.org/W1526237206","https://openalex.org/W7052389931","https://openalex.org/W2585236354","https://openalex.org/W2097730395","https://openalex.org/W4414330267","https://openalex.org/W2804222599","https://openalex.org/W1868766624"],"abstract_inverted_index":{"Record":[0,14],"linkage":[1,15,75,93],"refers":[2],"to":[3,33,129,139],"techniques":[4],"for":[5,74],"identifying":[6],"records":[7,107],"associated":[8,106],"with":[9],"the":[10,37,50,55,80,124,130,149],"same":[11],"real-world":[12],"entities.":[13],"is":[16,30],"not":[17],"only":[18],"crucial":[19],"in":[20,40,148],"integrating":[21,41],"multi-source":[22],"databases":[23],"that":[24,91],"have":[25],"been":[26],"generated":[27],"independently,":[28],"but":[29],"also":[31,146],"considered":[32],"be":[34],"one":[35],"of":[36,52,79,104,132],"key":[38],"issues":[39],"heterogeneous":[42],"Web":[43],"resources.":[44],"However,":[45],"when":[46],"targeting":[47],"large-scale":[48],"data,":[49],"cost":[51],"enumerating":[53],"all":[54],"possible":[56],"linkages":[57],"often":[58],"becomes":[59],"impracticably":[60],"high.":[61],"Based":[62],"on":[63],"this":[64,66],"background,":[65],"paper":[67],"proposes":[68],"a":[69,87],"fast":[70],"and":[71],"efficient":[72],"method":[73,126],"detection.":[76],"The":[77,117],"features":[78],"proposed":[81,125],"approach":[82],"are:":[83],"first,":[84],"it":[85,100],"exploits":[86],"suffix":[88],"array":[89],"structure":[90],"enables":[92],"detection":[94],"using":[95,108],"variable":[96],"length":[97],"n-grams.":[98],"Second,":[99],"dynamically":[101],"generates":[102],"blocks":[103],"possibly":[105],"\u2018blocking":[109],"keys\u2019":[110],"extracted":[111],"from":[112,119],"already":[113],"known":[114],"reliable":[115],"linkages.":[116],"results":[118],"our":[120],"preliminary":[121],"experiments":[122],"where":[123],"was":[127],"applied":[128],"integration":[131],"four":[133],"bibliographic":[134],"databases,":[135],"which":[136],"scale":[137],"up":[138],"more":[140],"than":[141],"10":[142],"million":[143],"records,":[144],"are":[145],"reported":[147],"paper.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":6}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2016-06-24T00:00:00"}
