{"id":"https://openalex.org/W254113056","doi":"https://doi.org/10.1145/1217299.1217304","title":"Collective entity resolution in relational data","display_name":"Collective entity resolution in relational data","publication_year":2007,"publication_date":"2007-03-01","ids":{"openalex":"https://openalex.org/W254113056","doi":"https://doi.org/10.1145/1217299.1217304","mag":"254113056"},"language":"en","primary_location":{"id":"doi:10.1145/1217299.1217304","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1217299.1217304","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"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":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://drum.lib.umd.edu/bitstreams/59d67557-bedd-4841-85e1-67f9dc238489/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101727281","display_name":"Indrajit Bhattacharya","orcid":"https://orcid.org/0009-0004-4279-538X"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Indrajit Bhattacharya","raw_affiliation_strings":["University of Maryland, College Park, MD","University of Maryland  College Park MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland  College Park MD","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086169451","display_name":"Lise Getoor","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lise Getoor","raw_affiliation_strings":["University of Maryland, College Park, MD","University of Maryland  College Park MD"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland  College Park MD","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":5.5275,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.95422168,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"1","issue":"1","first_page":"5","last_page":"5"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9965000152587891,"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/T11106","display_name":"Data Management and Algorithms","score":0.9952999949455261,"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":0.8597143888473511},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.6265043020248413},{"id":"https://openalex.org/keywords/entity\u2013relationship-model","display_name":"Entity\u2013relationship model","score":0.5802261233329773},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5684546232223511},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.5442594885826111},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5369956493377686},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5303186774253845},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4989168643951416},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.4979407787322998},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.45103392004966736},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.4491264820098877},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.42204469442367554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26232588291168213},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.09621262550354004},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09183928370475769}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8597143888473511},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.6265043020248413},{"id":"https://openalex.org/C103593891","wikidata":"https://www.wikidata.org/wiki/Q624546","display_name":"Entity\u2013relationship model","level":3,"score":0.5802261233329773},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5684546232223511},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.5442594885826111},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5369956493377686},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5303186774253845},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4989168643951416},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.4979407787322998},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.45103392004966736},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4491264820098877},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.42204469442367554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26232588291168213},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.09621262550354004},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09183928370475769},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1145/1217299.1217304","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1217299.1217304","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"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":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"},{"id":"pmh:oai:drum.lib.umd.edu:1903/4241","is_oa":true,"landing_page_url":"http://hdl.handle.net/1903/4241","pdf_url":"https://drum.lib.umd.edu/bitstreams/59d67557-bedd-4841-85e1-67f9dc238489/download","source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"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":"Dissertation"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.129.7844","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.129.7844","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.informatik.uni-freiburg.de/~ml/teaching/ss07/MLDMApps/papers/networks/p1-bhattacharya.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.215.1717","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.215.1717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.umd.edu/~indrajit/DOCS/debull06.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.87.1143","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.87.1143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://linqs.cs.umd.edu/basilic/web/Publications/2006/bhattacharya:thesis06/thesis.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.88.791","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.88.791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://waimea.cs.umd.edu:8080/basilic/web/Publications/2007/bhattacharya:tkdd07/bhattacharya-tkdd.pdf","raw_type":"text"},{"id":"mag:254113056","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:drum.lib.umd.edu:1903/4241","is_oa":true,"landing_page_url":"http://hdl.handle.net/1903/4241","pdf_url":"https://drum.lib.umd.edu/bitstreams/59d67557-bedd-4841-85e1-67f9dc238489/download","source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"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":"Dissertation"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W254113056.pdf","grobid_xml":"https://content.openalex.org/works/W254113056.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W46452414","https://openalex.org/W1536860849","https://openalex.org/W1559390933","https://openalex.org/W1561092886","https://openalex.org/W1564630549","https://openalex.org/W1569123402","https://openalex.org/W1606941371","https://openalex.org/W1646278814","https://openalex.org/W1761401273","https://openalex.org/W2001496424","https://openalex.org/W2024770506","https://openalex.org/W2036216970","https://openalex.org/W2046020929","https://openalex.org/W2052390074","https://openalex.org/W2052581258","https://openalex.org/W2055405704","https://openalex.org/W2067566391","https://openalex.org/W2073471108","https://openalex.org/W2097730395","https://openalex.org/W2102443632","https://openalex.org/W2102869387","https://openalex.org/W2105423800","https://openalex.org/W2123561513","https://openalex.org/W2133236963","https://openalex.org/W2135223301","https://openalex.org/W2148638861","https://openalex.org/W2150698190","https://openalex.org/W2152401660","https://openalex.org/W2154454189","https://openalex.org/W2154785834","https://openalex.org/W2159481891","https://openalex.org/W2164456230","https://openalex.org/W2168190036","https://openalex.org/W2170902582","https://openalex.org/W2420733993","https://openalex.org/W6633667658"],"related_works":["https://openalex.org/W2108991785","https://openalex.org/W2520082712","https://openalex.org/W2885895599","https://openalex.org/W1646278814","https://openalex.org/W3007025101","https://openalex.org/W3018042387","https://openalex.org/W2399003580","https://openalex.org/W2996993961","https://openalex.org/W2145124624","https://openalex.org/W2257503646","https://openalex.org/W2225606021","https://openalex.org/W2784165889","https://openalex.org/W3180878152","https://openalex.org/W1617896182","https://openalex.org/W2086322024","https://openalex.org/W3030713612","https://openalex.org/W2982138025","https://openalex.org/W2962831750","https://openalex.org/W2129244783","https://openalex.org/W2952526075"],"abstract_inverted_index":{"Many":[0],"databases":[1],"contain":[2],"uncertain":[3],"and":[4,45,67,138,147,190],"imprecise":[5],"references":[6,26,98,115],"to":[7,27,36,72,99,213],"real-world":[8,176],"entities.":[9,74],"The":[10],"absence":[11],"of":[12,56,85],"identifiers":[13],"for":[14,113,141],"the":[15,28,54,64,83,95,143,155],"underlying":[16,65,144],"entities":[17,66,76,101,112,201],"often":[18,90],"results":[19],"in":[20,42,94,110],"a":[21,129],"database":[22,70],"which":[23,111],"contains":[24],"multiple":[25,175],"same":[29],"entity.":[30],"This":[31],"can":[32,50,122],"lead":[33],"not":[34,199],"only":[35],"data":[37,212,215],"redundancy,":[38],"but":[39,197],"also":[40],"inaccuracies":[41],"query":[43],"processing":[44],"knowledge":[46],"extraction.":[47],"These":[48],"problems":[49],"be":[51],"alleviated":[52],"through":[53],"use":[55],"entity":[57,108,124,164,171,183],"resolution":[58,61,125,165,172,184,221],".":[59],"Entity":[60],"involves":[62],"discovering":[63],"mapping":[68],"each":[69],"reference":[71],"these":[73,105],"Traditionally,":[75],"are":[77,116],"resolved":[78],"using":[79],"pairwise":[80],"similarity":[81,160],"over":[82,186,191,222],"attributes":[84],"references.":[86],"However,":[87],"there":[88],"is":[89],"additional":[91],"relational":[92,131,139,159,195,220],"information":[93,140,196],"data.":[96],"Specifically,":[97],"different":[100,158],"may":[102],"cooccur.":[103],"In":[104,203],"cases,":[106],"collective":[107,170,219],"resolution,":[109],"cooccurring":[114],"determined":[117],"jointly":[118],"rather":[119],"than":[120],"independently,":[121],"improve":[123],"accuracy.":[126],"We":[127,153,167,178],"propose":[128],"novel":[130],"clustering":[132],"algorithm":[133,173],"that":[134,157,180,193,217],"uses":[135],"both":[136,187],"attribute":[137],"determining":[142],"domain":[145],"entities,":[146],"we":[148,205],"give":[149],"an":[150],"efficient":[151],"implementation.":[152],"investigate":[154],"impact":[156],"measures":[161],"have":[162],"on":[163,174,209],"quality.":[166],"evaluate":[168],"our":[169],"databases.":[177],"show":[179],"it":[181],"improves":[182],"performance":[185],"attribute-based":[188,224],"baselines":[189],"algorithms":[192],"consider":[194],"do":[198],"resolve":[200],"collectively.":[202],"addition,":[204],"perform":[206],"detailed":[207],"experiments":[208],"synthetically":[210],"generated":[211],"identify":[214],"characteristics":[216],"favor":[218],"purely":[223],"algorithms.":[225]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}