{"id":"https://openalex.org/W2086322024","doi":"https://doi.org/10.1109/tkde.2002.1000343","title":"A distance-based approach to entity reconciliation in heterogeneous databases","display_name":"A distance-based approach to entity reconciliation in heterogeneous databases","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2086322024","doi":"https://doi.org/10.1109/tkde.2002.1000343","mag":"2086322024"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2002.1000343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2002.1000343","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","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/A5061459812","display_name":"Debabrata Dey","orcid":"https://orcid.org/0000-0001-5290-0578"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"D. Dey","raw_affiliation_strings":["Administaration Department of Management science, University of Washington, Seattle, WA, USA","Dept. of Manage. Sci., Washington Univ., Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Administaration Department of Management science, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"Dept. of Manage. Sci., Washington Univ., Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053875023","display_name":"Sumit Sarkar","orcid":"https://orcid.org/0000-0003-3045-1024"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Sarkar","raw_affiliation_strings":["School of Management, University of Texas, Dallas, Richardson, TX, USA","[School of Management, University of Texas, Dallas, Richardson, TX, USA]"],"affiliations":[{"raw_affiliation_string":"School of Management, University of Texas, Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"[School of Management, University of Texas, Dallas, Richardson, TX, USA]","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076933277","display_name":"Prabuddha De","orcid":"https://orcid.org/0000-0002-0881-9294"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. De","raw_affiliation_strings":["School of Management, University of Texas, Dallas, Richardson, TX, USA","[School of Management, University of Texas, Dallas, Richardson, TX, USA]"],"affiliations":[{"raw_affiliation_string":"School of Management, University of Texas, Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"[School of Management, University of Texas, Dallas, Richardson, TX, USA]","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061459812"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":2.90631186,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.91459557,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"14","issue":"3","first_page":"567","last_page":"582"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9958000183105469,"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"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8571242094039917},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.6215985417366028},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5903934240341187},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5156639814376831},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48729145526885986},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3912610113620758},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37161511182785034},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35960811376571655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22787365317344666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8571242094039917},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.6215985417366028},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5903934240341187},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5156639814376831},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48729145526885986},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3912610113620758},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37161511182785034},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35960811376571655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22787365317344666},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2002.1000343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2002.1000343","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7900000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309636","display_name":"University of Minnesota","ror":"https://ror.org/03grvy078"},{"id":"https://openalex.org/F4320310094","display_name":"University of Washington","ror":"https://ror.org/00cvxb145"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W29390303","https://openalex.org/W158727920","https://openalex.org/W1495788210","https://openalex.org/W1513756412","https://openalex.org/W1537402732","https://openalex.org/W1599398663","https://openalex.org/W1716873180","https://openalex.org/W1768893245","https://openalex.org/W1967608956","https://openalex.org/W1985108724","https://openalex.org/W1993637408","https://openalex.org/W2013727301","https://openalex.org/W2015656470","https://openalex.org/W2015914309","https://openalex.org/W2016758618","https://openalex.org/W2024770506","https://openalex.org/W2036902446","https://openalex.org/W2038281398","https://openalex.org/W2047965058","https://openalex.org/W2051559922","https://openalex.org/W2052390074","https://openalex.org/W2069323107","https://openalex.org/W2073471108","https://openalex.org/W2075038844","https://openalex.org/W2075043418","https://openalex.org/W2076898857","https://openalex.org/W2080477440","https://openalex.org/W2088143891","https://openalex.org/W2089634871","https://openalex.org/W2112440119","https://openalex.org/W2118587067","https://openalex.org/W2119515731","https://openalex.org/W2125690626","https://openalex.org/W2132610455","https://openalex.org/W2150698190","https://openalex.org/W2158494365","https://openalex.org/W2168936936","https://openalex.org/W2222512263","https://openalex.org/W2285786022","https://openalex.org/W2313094819","https://openalex.org/W2331257008","https://openalex.org/W2913066018","https://openalex.org/W4206520518","https://openalex.org/W4230502578","https://openalex.org/W4236310305","https://openalex.org/W4252521233","https://openalex.org/W4292157289","https://openalex.org/W6632403346","https://openalex.org/W6672676662","https://openalex.org/W6817337975"],"related_works":["https://openalex.org/W4378651134","https://openalex.org/W1979633005","https://openalex.org/W2352307597","https://openalex.org/W2163724607","https://openalex.org/W1980092392","https://openalex.org/W2608983118","https://openalex.org/W4318812462","https://openalex.org/W37347591","https://openalex.org/W2118976126","https://openalex.org/W4252684102"],"abstract_inverted_index":{"In":[0],"modern":[1],"organizations,":[2],"decision":[3],"makers":[4],"must":[5,48],"often":[6],"be":[7,142,151],"able":[8],"to":[9,18,32,90,102,135,150,158],"quickly":[10],"access":[11],"information":[12,36],"from":[13,161],"diverse":[14],"sources":[15],"in":[16,38,84,130,181],"order":[17],"make":[19],"timely":[20],"decisions.":[21],"A":[22,87],"critical":[23],"problem":[24,65,93],"facing":[25],"many":[26],"such":[27,64],"organizations":[28],"is":[29,79,94,148,176],"the":[30,35,67,74,92,104,113,125,162,165,170],"inability":[31],"easily":[33],"reconcile":[34],"contained":[37],"heterogeneous":[39],"data":[40],"sources.":[41,60],"To":[42],"overcome":[43],"this":[44,175],"limitation,":[45],"an":[46],"organization":[47],"resolve":[49,91],"several":[50],"types":[51],"of":[52,132,164,167],"heterogeneity":[53,69],"problems":[54],"that":[55,124,174],"may":[56],"exist":[57],"across":[58],"different":[59,82,85],"We":[61,110],"examine":[62],"one":[63],"called":[66],"entity":[68,77,108,139],"problem,":[70],"which":[71],"arises":[72],"when":[73],"same":[75],"real-world":[76,119],"type":[78],"represented":[80],"using":[81],"identifiers":[83],"applications.":[86],"decision-theoretic":[88],"model":[89,97,114,126,147],"proposed.":[95],"Our":[96],"uses":[98],"a":[99,178],"distance":[100],"measure":[101],"express":[103],"similarity":[105],"between":[106],"two":[107,138],"instances.":[109],"have":[111],"implemented":[112],"and":[115],"tested":[116],"it":[117],"on":[118],"data.":[120],"The":[121,146],"results":[122,172],"indicate":[123],"performs":[127],"quite":[128],"well":[129,157],"terms":[131],"its":[133],"ability":[134],"predict":[136],"whether":[137],"instances":[140],"should":[141],"matched":[143],"or":[144],"not.":[145],"shown":[149],"computationally":[152],"efficient.":[153],"It":[154],"also":[155],"scales":[156],"large":[159],"relations":[160],"perspective":[163],"accuracy":[166],"prediction.":[168],"Overall,":[169],"test":[171],"imply":[173],"certainly":[177],"viable":[179],"approach":[180],"practical":[182],"situations.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}