{"id":"https://openalex.org/W1966051303","doi":"https://doi.org/10.1109/bigdata.2014.7004459","title":"Probabilistic estimates of attribute statistics and match likelihood for people entity resolution","display_name":"Probabilistic estimates of attribute statistics and match likelihood for people entity resolution","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W1966051303","doi":"https://doi.org/10.1109/bigdata.2014.7004459","mag":"1966051303"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2014.7004459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","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/A5100327905","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-1665-8398"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xin Wang","raw_affiliation_strings":["Data Research, Intelius Inc., Bellevue, WA","Data Research, Intelius Inc, Bellevue, WA"],"affiliations":[{"raw_affiliation_string":"Data Research, Intelius Inc., Bellevue, WA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Data Research, Intelius Inc, Bellevue, WA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002868174","display_name":"Ang Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ang Sun","raw_affiliation_strings":["Data Research, Intelius Inc., Bellevue, WA","Data Research, Intelius Inc, Bellevue, WA"],"affiliations":[{"raw_affiliation_string":"Data Research, Intelius Inc., Bellevue, WA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Data Research, Intelius Inc, Bellevue, WA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038628557","display_name":"Hakan Kardes","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hakan Kardes","raw_affiliation_strings":["Data Research, Intelius Inc., Bellevue, WA","Data Research, Intelius Inc, Bellevue, WA"],"affiliations":[{"raw_affiliation_string":"Data Research, Intelius Inc., Bellevue, WA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Data Research, Intelius Inc, Bellevue, WA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018019178","display_name":"Siddharth Agrawal","orcid":"https://orcid.org/0000-0002-6068-1253"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Agrawal","raw_affiliation_strings":["Data Research, Intelius Inc., Bellevue, WA","Data Research, Intelius Inc, Bellevue, WA"],"affiliations":[{"raw_affiliation_string":"Data Research, Intelius Inc., Bellevue, WA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Data Research, Intelius Inc, Bellevue, WA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443817","display_name":"Lin Chen","orcid":"https://orcid.org/0000-0003-4330-1519"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lin Chen","raw_affiliation_strings":["Data Research, Intelius Inc., Bellevue, WA","Data Research, Intelius Inc, Bellevue, WA"],"affiliations":[{"raw_affiliation_string":"Data Research, Intelius Inc., Bellevue, WA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Data Research, Intelius Inc, Bellevue, WA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035143245","display_name":"Andrew Borthwick","orcid":"https://orcid.org/0000-0003-1192-0032"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Borthwick","raw_affiliation_strings":["Data Research, Intelius Inc., Bellevue, WA","Data Research, Intelius Inc, Bellevue, WA"],"affiliations":[{"raw_affiliation_string":"Data Research, Intelius Inc., Bellevue, WA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Data Research, Intelius Inc, Bellevue, WA","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100327905"],"corresponding_institution_ids":["https://openalex.org/I1343180700"],"apc_list":null,"apc_paid":null,"fwci":0.4204,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68002501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"6","issue":null,"first_page":"92","last_page":"99"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.987500011920929,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9679999947547913,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7269797921180725},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7096551656723022},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.589942216873169},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5708493590354919},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.57041335105896},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.5623515844345093},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4988133907318115},{"id":"https://openalex.org/keywords/likelihood-function","display_name":"Likelihood function","score":0.4977429211139679},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4947187602519989},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.46462661027908325},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4010798931121826},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2216276228427887},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1863427758216858},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.17648732662200928},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.16106104850769043},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14365842938423157},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07917612791061401}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7269797921180725},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7096551656723022},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.589942216873169},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5708493590354919},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.57041335105896},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.5623515844345093},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4988133907318115},{"id":"https://openalex.org/C89106044","wikidata":"https://www.wikidata.org/wiki/Q45284","display_name":"Likelihood function","level":3,"score":0.4977429211139679},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4947187602519989},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.46462661027908325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4010798931121826},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2216276228427887},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1863427758216858},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.17648732662200928},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.16106104850769043},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14365842938423157},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07917612791061401},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata.2014.7004459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.710.829","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.710.829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.unr.edu/%7Ehkardes/pdfs/nameFreq.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W822439496","https://openalex.org/W1521736627","https://openalex.org/W1967647772","https://openalex.org/W1984775058","https://openalex.org/W1992930793","https://openalex.org/W2024770506","https://openalex.org/W2046020929","https://openalex.org/W2073545563","https://openalex.org/W2095644746","https://openalex.org/W2101654853","https://openalex.org/W2108991785","https://openalex.org/W2111032703","https://openalex.org/W2148019918","https://openalex.org/W2155189155","https://openalex.org/W2162237605","https://openalex.org/W2164456230","https://openalex.org/W2169585110","https://openalex.org/W2251214202","https://openalex.org/W2397525010","https://openalex.org/W2951943777","https://openalex.org/W3146259567","https://openalex.org/W4230502578","https://openalex.org/W4249682906","https://openalex.org/W4301673059","https://openalex.org/W6623203846"],"related_works":["https://openalex.org/W3161249280","https://openalex.org/W2267059662","https://openalex.org/W2375480909","https://openalex.org/W2364268683","https://openalex.org/W4388411807","https://openalex.org/W2353314428","https://openalex.org/W1519906715","https://openalex.org/W2478803962","https://openalex.org/W2606460416","https://openalex.org/W2387801216"],"abstract_inverted_index":{"For":[0],"big":[1],"data":[2,4,120],"practitioners,":[3],"integration/entity":[5],"resolution/record":[6,21],"linkage":[7,22],"is":[8,50,131],"one":[9],"of":[10,34,38,68,71,76,84,91,94,150],"the":[11,52,65,85,89,92,95,101,109,125,134,142,148,151],"key":[12],"challenges":[13],"we":[14],"face":[15],"from":[16],"day":[17],"to":[18,63,107,122],"day.":[19],"Entity":[20],"with":[23,32],"high":[24],"precision":[25],"and":[26,36,79],"recall":[27,149],"on":[28,88,116],"a":[29,60,69],"large":[30],"graph":[31,48],"billions":[33],"nodes,":[35],"hundreds":[37],"times":[39],"more":[40],"edges":[41],"poses":[42],"significant":[43],"scalability":[44],"challenges.":[45],"Similarity":[46],"based":[47,115],"partition":[49],"still":[51],"most":[53],"scalable":[54],"method":[55,62],"available.":[56],"This":[57],"paper":[58,99],"presents":[59],"probabilistic":[61],"approximate":[64,143],"match":[66,144],"likelihood":[67,145],"pair":[70],"records":[72],"by":[73],"incorporating":[74],"values":[75],"different":[77],"attributes":[78],"their":[80],"aggregates/statistics.":[81],"The":[82,98],"quality":[83],"approximates":[86],"depend":[87],"accuracy":[90],"estimates":[93,126],"aggregated":[96],"values.":[97],"adapts":[100],"GTM":[102,129],"model":[103,130],"described":[104],"in":[105],"[1]":[106],"obtain":[108],"estimates.":[110],"We":[111],"present":[112],"experimental":[113,137],"results":[114,138],"real":[117],"world":[118],"commercial":[119],"sources":[121],"show":[123],"that":[124,141],"obtained":[127],"via":[128],"better":[132],"than":[133],"baseline.":[135],"Our":[136],"also":[139],"showed":[140],"can":[146],"improve":[147],"similarity":[152],"function.":[153]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}