{"id":"https://openalex.org/W2040925009","doi":"https://doi.org/10.1109/icde.2007.367865","title":"Source-aware Entity Matching: A Compositional Approach","display_name":"Source-aware Entity Matching: A Compositional Approach","publication_year":2007,"publication_date":"2007-04-01","ids":{"openalex":"https://openalex.org/W2040925009","doi":"https://doi.org/10.1109/icde.2007.367865","mag":"2040925009"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2007.367865","doi":"https://doi.org/10.1109/icde.2007.367865","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2007.367865","pdf_url":null,"source":{"id":"https://openalex.org/S4210210321","display_name":"IEEE International Conference on Data Engineering (ICDE)","issn_l":"1084-4627","issn":["1084-4627","2375-0286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"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":"2007 IEEE 23rd International Conference on Data Engineering","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/A5110502431","display_name":"Warren Shen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Warren Shen","raw_affiliation_strings":["University of Wisconsin, Madison, USA","[Wisconsin Univ., Madison, WI, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin, Madison, USA","institution_ids":["https://openalex.org/I135310074"]},{"raw_affiliation_string":"[Wisconsin Univ., Madison, WI, USA]","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051215177","display_name":"Pedro DeRose","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pedro DeRose","raw_affiliation_strings":["University of Wisconsin, Madison, USA","[Wisconsin Univ., Madison, WI, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin, Madison, USA","institution_ids":["https://openalex.org/I135310074"]},{"raw_affiliation_string":"[Wisconsin Univ., Madison, WI, USA]","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038966811","display_name":"Long Vu","orcid":"https://orcid.org/0000-0002-3586-8630","observed_orcids":["https://orcid.org/0000-0002-3586-8630"]},"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":"Long Vu","raw_affiliation_strings":["University of Illinois, Urbana, USA","Madison University of Illinois"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Madison University of Illinois","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110256670","display_name":"AnHai Doan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"AnHai Doan","raw_affiliation_strings":["University of Wisconsin, Madison, USA","University of Wisconsin \u2013,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin, Madison, USA","institution_ids":["https://openalex.org/I135310074"]},{"raw_affiliation_string":"University of Wisconsin \u2013,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051301731","display_name":"Raghu Ramakrishnan","orcid":"https://orcid.org/0009-0007-5086-7664","observed_orcids":["https://orcid.org/0009-0007-5086-7664"]},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raghu Ramakrishnan","raw_affiliation_strings":["Yahoo Research, Inc., USA","Urbana Yahoo! Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research, Inc., USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Urbana Yahoo! Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.4307,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.97284696,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"196","last_page":"205"},"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/T10028","display_name":"Topic Modeling","score":0.0,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.0,"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/entity-resolution","display_name":"entity resolution","score":0.9959999918937683},{"id":"https://openalex.org/keywords/data-linkage","display_name":"data linkage","score":0.9990000128746033},{"id":"https://openalex.org/keywords/data-source-selection","display_name":"data source selection","score":0.578000009059906},{"id":"https://openalex.org/keywords/social-network-analysis","display_name":"social network analysis","score":0.871999979019165},{"id":"https://openalex.org/keywords/personal-information-management","display_name":"personal information management","score":0.8970000147819519},{"id":"https://openalex.org/keywords/data-integration","display_name":"data integration","score":0.6320000290870667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8371808528900146},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.7838640809059143},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.7385956048965454},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6361624002456665},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.5621163845062256},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5511002540588379},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5258781909942627},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.49664145708084106},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.48968198895454407},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4685951769351959},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.4504566490650177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2340349555015564},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icde.2007.367865","doi":"https://doi.org/10.1109/icde.2007.367865","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2007.367865","pdf_url":null,"source":{"id":"https://openalex.org/S4210210321","display_name":"IEEE International Conference on Data Engineering (ICDE)","issn_l":"1084-4627","issn":["1084-4627","2375-0286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"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":"2007 IEEE 23rd International Conference on Data Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.104.608","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.104.608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dedrop.org/papers/soccer-icde07.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.131.2220","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.131.2220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.wisc.edu/~anhai/papers/soccer-icde07.pdf","raw_type":"text"},{"id":"pmh:oai:minds.wisc.edu:1793/60494","doi":null,"is_oa":false,"landing_page_url":"http://digital.library.wisc.edu/1793/60494","pdf_url":null,"source":{"id":"https://openalex.org/S4306401622","display_name":"Minds at UW (University of Wisconsin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I135310074","host_organization_name":"University of Wisconsin\u2013Madison","host_organization_lineage":["https://openalex.org/I135310074"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Technical Report"}],"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":35,"referenced_works":["https://openalex.org/W130948412","https://openalex.org/W950821216","https://openalex.org/W1485156179","https://openalex.org/W1488272912","https://openalex.org/W1539585011","https://openalex.org/W1551385575","https://openalex.org/W1557103245","https://openalex.org/W1689241477","https://openalex.org/W1854214752","https://openalex.org/W1973828215","https://openalex.org/W1999823970","https://openalex.org/W2024770506","https://openalex.org/W2027864253","https://openalex.org/W2029873015","https://openalex.org/W2030724586","https://openalex.org/W2036216970","https://openalex.org/W2038281398","https://openalex.org/W2046020929","https://openalex.org/W2061901927","https://openalex.org/W2065290081","https://openalex.org/W2102462631","https://openalex.org/W2102869387","https://openalex.org/W2105577993","https://openalex.org/W2111625757","https://openalex.org/W2121516976","https://openalex.org/W2123561513","https://openalex.org/W2124410446","https://openalex.org/W2129598390","https://openalex.org/W2135223301","https://openalex.org/W2159481891","https://openalex.org/W2161600801","https://openalex.org/W2161936973","https://openalex.org/W2166994031","https://openalex.org/W4232413872","https://openalex.org/W6629262490"],"related_works":["https://openalex.org/W2803421404","https://openalex.org/W2473455520","https://openalex.org/W2982247189","https://openalex.org/W2983211929","https://openalex.org/W4387424895","https://openalex.org/W2104511295","https://openalex.org/W7096499345","https://openalex.org/W4210409105","https://openalex.org/W2197151308","https://openalex.org/W4414910845"],"abstract_inverted_index":{"Entity":[0],"matching":[1,16,37,51,72,101,120,199],"(a.k.a.":[2],"record":[3],"linkage)":[4],"plays":[5],"a":[6,35,97,113,122,128,145],"crucial":[7],"role":[8],"in":[9,30,63,85,181],"integrating":[10],"multiple":[11],"data":[12,46,166,175],"sources,":[13],"and":[14,33,82,140,163,180],"numerous":[15],"solutions":[17,23],"have":[18,24],"been":[19],"developed.":[20],"However,":[21],"the":[22,31,105,137,161,178,182],"largely":[25],"exploited":[26],"only":[27],"information":[28,44,186],"available":[29],"mentions":[32,84],"employed":[34],"single":[36],"technique.":[38],"We":[39,116,132,168],"show":[40,141,191],"how":[41,142],"to":[42,48,80,96,104,143,159],"exploit":[43],"about":[45],"sources":[47,59,87],"significantly":[49,195],"improve":[50],"accuracy.":[52],"In":[53,74],"particular,":[54],"we":[55,152],"observe":[56],"that":[57,192],"different":[58,71],"often":[60,78],"vary":[61],"substantially":[62],"their":[64],"level":[65],"of":[66,100,107,124,136,165,184],"semantic":[67],"ambiguity,":[68],"thus":[69],"requiring":[70],"techniques.":[73],"addition,":[75],"it":[76],"is":[77],"beneficial":[79],"group":[81],"match":[83,147],"related":[86],"first,":[88],"before":[89],"considering":[90],"other":[91],"sources.":[92,167],"These":[93],"observations":[94],"lead":[95],"large":[98],"space":[99,106],"strategies,":[102],"analogous":[103],"query":[108],"evaluation":[109],"plans":[110],"considered":[111],"by":[112],"relational":[114],"optimizer.":[115],"propose":[117],"viewing":[118],"entity":[119],"as":[121],"composition":[123],"basic":[125],"steps":[126],"into":[127],"\"match":[129],"execution":[130],"plan\".":[131],"analyze":[133],"formal":[134],"properties":[135],"plan":[138],"space,":[139],"find":[144],"good":[146],"plan.":[148],"To":[149],"do":[150],"so,":[151],"employ":[153],"ideas":[154],"from":[155],"social":[156],"network":[157],"analysis":[158],"infer":[160],"ambiguity":[162],"related-ness":[164],"conducted":[169],"extensive":[170],"experiments":[171],"on":[172,177],"several":[173],"real-world":[174],"sets":[176],"Web":[179],"domain":[183],"personal":[185],"management":[187],"(PIM).":[188],"The":[189],"results":[190],"our":[193],"solution":[194],"outperforms":[196],"current":[197],"best":[198],"methods.":[200]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2016-06-24T00:00:00"}