{"id":"https://openalex.org/W1985323106","doi":"https://doi.org/10.1145/2247596.2247639","title":"Aggregate queries on probabilistic record linkages","display_name":"Aggregate queries on probabilistic record linkages","publication_year":2012,"publication_date":"2012-03-27","ids":{"openalex":"https://openalex.org/W1985323106","doi":"https://doi.org/10.1145/2247596.2247639","mag":"1985323106"},"language":"en","primary_location":{"id":"doi:10.1145/2247596.2247639","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2247596.2247639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Extending Database Technology","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/A5102765393","display_name":"Hua Ming","orcid":"https://orcid.org/0000-0001-5379-6311"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Hua","raw_affiliation_strings":["Facebook Inc., Menlo Park, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Inc., Menlo Park, CA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062247330","display_name":"Jian Pei","orcid":"https://orcid.org/0000-0002-2200-8711"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jian Pei","raw_affiliation_strings":["Simon Fraser University, Burnaby, BC, Canada","[Simon Fraser University Burnaby, BC, Canada]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Burnaby, BC, Canada","institution_ids":["https://openalex.org/I18014758"]},{"raw_affiliation_string":"[Simon Fraser University Burnaby, BC, Canada]","institution_ids":["https://openalex.org/I18014758"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.828,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75635291,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"360","last_page":"371"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9546999931335449,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9517999887466431,"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/record-linkage","display_name":"Record linkage","score":0.873557448387146},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7754844427108765},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7275926470756531},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.7081104516983032},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.6992844939231873},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.6114515066146851},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5777766704559326},{"id":"https://openalex.org/keywords/real-world-data","display_name":"Real world data","score":0.4859682321548462},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40530163049697876},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36903345584869385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24195751547813416},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.1916433870792389},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06417077779769897},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.061979204416275024}],"concepts":[{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.873557448387146},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7754844427108765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7275926470756531},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.7081104516983032},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.6992844939231873},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.6114515066146851},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5777766704559326},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.4859682321548462},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40530163049697876},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36903345584869385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24195751547813416},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.1916433870792389},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06417077779769897},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.061979204416275024},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2247596.2247639","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2247596.2247639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Conference on Extending Database Technology","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.300.1670","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.300.1670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.sfu.ca/~jpei/publications/u-linkage-edbt12.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.366.2002","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.366.2002","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.edbt.org/Proceedings/2012-Berlin/papers/edbt/a12-hua.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W36024057","https://openalex.org/W93564379","https://openalex.org/W981005881","https://openalex.org/W1490591387","https://openalex.org/W1513861746","https://openalex.org/W1567885833","https://openalex.org/W1647671624","https://openalex.org/W1673955757","https://openalex.org/W1968461475","https://openalex.org/W1974688422","https://openalex.org/W2007682403","https://openalex.org/W2008881282","https://openalex.org/W2023448865","https://openalex.org/W2026808466","https://openalex.org/W2030164976","https://openalex.org/W2034143386","https://openalex.org/W2044494469","https://openalex.org/W2050290319","https://openalex.org/W2073471108","https://openalex.org/W2078667951","https://openalex.org/W2098333994","https://openalex.org/W2101366610","https://openalex.org/W2102350406","https://openalex.org/W2114242687","https://openalex.org/W2115986770","https://openalex.org/W2120825705","https://openalex.org/W2125189508","https://openalex.org/W2129035130","https://openalex.org/W2153508518","https://openalex.org/W2154785834","https://openalex.org/W2161936973","https://openalex.org/W2164456230","https://openalex.org/W2171265988","https://openalex.org/W2171776999","https://openalex.org/W2215822900","https://openalex.org/W2611200784","https://openalex.org/W4230389186","https://openalex.org/W4285719527","https://openalex.org/W4297792526","https://openalex.org/W4302466655"],"related_works":["https://openalex.org/W2353179089","https://openalex.org/W2487032012","https://openalex.org/W2211355040","https://openalex.org/W2808916796","https://openalex.org/W2176311362","https://openalex.org/W3012491082","https://openalex.org/W3211905090","https://openalex.org/W1936317645","https://openalex.org/W4310568775","https://openalex.org/W2178148352"],"abstract_inverted_index":{"Record":[0],"linkage":[1,42],"analysis,":[2],"which":[3],"matches":[4],"records":[5,52],"referring":[6,53],"to":[7,31,54],"the":[8,38,48,55],"same":[9,56],"real":[10],"world":[11],"entities":[12],"from":[13],"different":[14],"data":[15,22],"sets,":[16],"is":[17],"an":[18],"important":[19],"task":[20],"in":[21,27,35],"integration.":[23],"Uncertainty":[24],"often":[25],"exists":[26],"record":[28,41],"linkages":[29],"due":[30],"incompleteness":[32],"or":[33],"ambiguity":[34],"data.":[36],"Fortunately,":[37],"state-of-the-art":[39],"probabilistic":[40],"methods":[43],"are":[44],"capable":[45],"of":[46],"computing":[47],"probability":[49],"that":[50],"two":[51],"entity.":[57]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
