{"id":"https://openalex.org/W1976030875","doi":"https://doi.org/10.1109/cts.2014.6867546","title":"Large-scale entity extraction and probabilistic record linkage","display_name":"Large-scale entity extraction and probabilistic record linkage","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W1976030875","doi":"https://doi.org/10.1109/cts.2014.6867546","mag":"1976030875"},"language":"en","primary_location":{"id":"doi:10.1109/cts.2014.6867546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cts.2014.6867546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Collaboration Technologies and Systems (CTS)","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/A5073869382","display_name":"Flavio Villanustre","orcid":"https://orcid.org/0000-0003-4373-4250"},"institutions":[{"id":"https://openalex.org/I4210160498","display_name":"RELX Group (United States)","ror":"https://ror.org/05k2n4n22","country_code":"US","type":"company","lineage":["https://openalex.org/I4210160498","https://openalex.org/I4210160603"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Flavio Villanustre","raw_affiliation_strings":["Reed Elsevier LexisNexis Risk Solutions Alpharetta, GA, USA","[Reed Elsevier LexisNexis Risk Solutions Alpharetta, GA, USA]"],"affiliations":[{"raw_affiliation_string":"Reed Elsevier LexisNexis Risk Solutions Alpharetta, GA, USA","institution_ids":["https://openalex.org/I4210160498"]},{"raw_affiliation_string":"[Reed Elsevier LexisNexis Risk Solutions Alpharetta, GA, USA]","institution_ids":["https://openalex.org/I4210160498"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5073869382"],"corresponding_institution_ids":["https://openalex.org/I4210160498"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09487898,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"85","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"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":0.9994000196456909,"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":0.968999981880188,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9132999777793884,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8195587396621704},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5716753005981445},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.5693640112876892},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5524503588676453},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.5061292052268982},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4943368434906006},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.475923091173172},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4615604281425476},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.45995867252349854},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4592658281326294},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.449382483959198},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35913586616516113},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.2732371687889099},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26171791553497314}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8195587396621704},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5716753005981445},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.5693640112876892},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5524503588676453},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.5061292052268982},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4943368434906006},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.475923091173172},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4615604281425476},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.45995867252349854},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4592658281326294},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.449382483959198},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35913586616516113},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2732371687889099},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26171791553497314},{"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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"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/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"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":1,"locations":[{"id":"doi:10.1109/cts.2014.6867546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cts.2014.6867546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Collaboration Technologies and Systems (CTS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2591697403","https://openalex.org/W2944728705","https://openalex.org/W2904022177","https://openalex.org/W2359348847","https://openalex.org/W3011538607","https://openalex.org/W4294432981","https://openalex.org/W4321441197","https://openalex.org/W2953716828","https://openalex.org/W2469820710","https://openalex.org/W4321276295"],"abstract_inverted_index":{"Summary":[0],"form":[1],"only":[2],"given.":[3],"Large-scale":[4],"entity":[5,96],"extraction,":[6,97],"disambiguation":[7],"and":[8,48,63,99,126,128],"linkage":[9,100,136],"in":[10,26],"Big":[11,89],"Data":[12,39,41],"can":[13],"challenge":[14],"the":[15,20,73,76,112,117,130,142],"traditional":[16],"methodologies":[17],"developed":[18],"over":[19,67],"last":[21],"three":[22],"decades.":[23],"Entity":[24],"linkage,":[25,81,87],"particular,":[27],"is":[28],"cornerstone":[29],"for":[30],"a":[31,108,138],"wide":[32],"spectrum":[33],"of":[34,78],"applications,":[35],"such":[36],"as":[37,84],"Master":[38],"Management,":[40],"Warehousing,":[42],"Social":[43],"Graph":[44],"Analytics,":[45],"Fraud":[46],"Detection":[47],"Identity":[49],"Management.":[50],"Traditional":[51],"rules":[52],"based":[53,86],"heuristic":[54],"methods":[55],"usually":[56],"don't":[57],"scale":[58],"properly,":[59],"are":[60],"language":[61,93],"specific":[62],"require":[64],"significant":[65],"maintenance":[66],"time.":[68],"This":[69],"presentation":[70,105],"will":[71],"introduce":[72],"audience":[74],"to":[75,91],"use":[77],"probabilistic":[79,134],"record":[80,135],"also":[82,106],"known":[83],"specificity":[85],"on":[88,137],"Data,":[90],"perform":[92],"independent":[94],"large-scale":[95],"resolution":[98],"across":[101],"diverse":[102],"sources.":[103],"The":[104],"includes":[107],"live":[109],"demonstration":[110],"reviewing":[111],"different":[113],"steps":[114],"required":[115],"during":[116],"data":[118,146],"integration":[119],"process":[120],"(ingestion,":[121],"profiling,":[122],"parsing,":[123],"cleansing,":[124],"standardization":[125],"normalization),":[127],"show":[129],"basic":[131],"concepts":[132],"behind":[133],"real-world":[139],"application":[140],"using":[141],"open":[143],"source":[144],"big":[145],"platform,":[147],"HPCC":[148],"Systems":[149],"[1]":[150],"from":[151],"LexisNexis.":[152]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
