{"id":"https://openalex.org/W2605690107","doi":"https://doi.org/10.1007/s41060-018-0129-7","title":"Unsupervised record matching with noisy and incomplete data","display_name":"Unsupervised record matching with noisy and incomplete data","publication_year":2018,"publication_date":"2018-05-23","ids":{"openalex":"https://openalex.org/W2605690107","doi":"https://doi.org/10.1007/s41060-018-0129-7","mag":"2605690107"},"language":"en","primary_location":{"id":"doi:10.1007/s41060-018-0129-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41060-018-0129-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41060-018-0129-7.pdf","source":{"id":"https://openalex.org/S4210195017","display_name":"International Journal of Data Science and Analytics","issn_l":"2364-415X","issn":["2364-415X","2364-4168"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Science and Analytics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s41060-018-0129-7.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054207716","display_name":"Yves van Gennip","orcid":"https://orcid.org/0000-0003-4953-8314"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yves van Gennip","raw_affiliation_strings":["University of Nottingham, Nottingham, UK"],"raw_orcid":"https://orcid.org/0000-0003-4953-8314","affiliations":[{"raw_affiliation_string":"University of Nottingham, Nottingham, UK","institution_ids":["https://openalex.org/I142263535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005758423","display_name":"Blake Hunter","orcid":null},"institutions":[{"id":"https://openalex.org/I106107269","display_name":"Claremont McKenna College","ror":"https://ror.org/04n1me355","country_code":"US","type":"education","lineage":["https://openalex.org/I106107269"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Blake Hunter","raw_affiliation_strings":["Claremont McKenna College, Claremont, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Claremont McKenna College, Claremont, USA","institution_ids":["https://openalex.org/I106107269"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103201778","display_name":"Anna Ma","orcid":"https://orcid.org/0000-0002-0099-053X"},"institutions":[{"id":"https://openalex.org/I136722135","display_name":"Claremont Graduate University","ror":"https://ror.org/0157pnt69","country_code":"US","type":"education","lineage":["https://openalex.org/I136722135"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anna Ma","raw_affiliation_strings":["Claremont Graduate University, Claremont, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Claremont Graduate University, Claremont, USA","institution_ids":["https://openalex.org/I136722135"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072158791","display_name":"Daniel Moyer","orcid":"https://orcid.org/0000-0003-4428-5012"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Moyer","raw_affiliation_strings":["University of Southern California, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042068017","display_name":"Ryan de Vera","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryan de Vera","raw_affiliation_strings":["Hush, Inc., Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hush, Inc., Los Angeles, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090707978","display_name":"Andrea L. Bertozzi","orcid":"https://orcid.org/0000-0003-0396-7391"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrea L. Bertozzi","raw_affiliation_strings":["University of California, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5054207716"],"corresponding_institution_ids":["https://openalex.org/I142263535"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":1.1415,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.79496695,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"6","issue":"2","first_page":"109","last_page":"129"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9962000250816345,"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"}},{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9876999855041504,"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":0.749734103679657},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6569243669509888},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6493013501167297},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5901902318000793},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5746864080429077},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5535222291946411},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.5280987620353699},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5045047998428345},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4903159439563751},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.45441707968711853},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41043341159820557},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37341541051864624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.360927551984787},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.208023339509964},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1416795551776886},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12157082557678223}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.749734103679657},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6569243669509888},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6493013501167297},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5901902318000793},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5746864080429077},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5535222291946411},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.5280987620353699},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5045047998428345},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4903159439563751},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.45441707968711853},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41043341159820557},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37341541051864624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.360927551984787},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.208023339509964},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1416795551776886},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12157082557678223},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s41060-018-0129-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41060-018-0129-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41060-018-0129-7.pdf","source":{"id":"https://openalex.org/S4210195017","display_name":"International Journal of Data Science and Analytics","issn_l":"2364-415X","issn":["2364-415X","2364-4168"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Science and Analytics","raw_type":"journal-article"},{"id":"pmh:oai:eprints.nottingham.ac.uk:51471","is_oa":true,"landing_page_url":"https://link.springer.com/article/10.1007/s41060-018-0129-7","pdf_url":null,"source":{"id":"https://openalex.org/S4306402014","display_name":"Nottingham ePrints (University of Nottingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142263535","host_organization_name":"University of Nottingham","host_organization_lineage":["https://openalex.org/I142263535"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:nottingham-repository.worktribe.com:933965","is_oa":true,"landing_page_url":"https://nottingham-repository.worktribe.com/output/933965","pdf_url":null,"source":{"id":"https://openalex.org/S4306402483","display_name":"Repository@Nottingham (University of Nottingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142263535","host_organization_name":"University of Nottingham","host_organization_lineage":["https://openalex.org/I142263535"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1007/s41060-018-0129-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41060-018-0129-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41060-018-0129-7.pdf","source":{"id":"https://openalex.org/S4210195017","display_name":"International Journal of Data Science and Analytics","issn_l":"2364-415X","issn":["2364-415X","2364-4168"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Science and Analytics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1523888516","display_name":null,"funder_award_id":"FA9550-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G2600073730","display_name":null,"funder_award_id":"N00014-16-1-2119","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G3392305090","display_name":null,"funder_award_id":"-16-1-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G5212771377","display_name":null,"funder_award_id":"FA9550-10-1-0569","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G5809100787","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G5948696453","display_name":null,"funder_award_id":"DMS-1737770","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6098521345","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G7741864895","display_name":null,"funder_award_id":"FA9550-10-1-0569","funder_id":"https://openalex.org/F4320333591","funder_display_name":"Multidisciplinary University Research Initiative"},{"id":"https://openalex.org/G781543995","display_name":"California Research Training Program in Computational and Applied Mathematics","funder_award_id":"1045536","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8488940573","display_name":null,"funder_award_id":"DMS-1045536","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8570927041","display_name":null,"funder_award_id":"DMS-1417674","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8802953049","display_name":"Extreme-scale algorithms for geometric graphical data models in imaging, social and network science","funder_award_id":"1417674","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8998889701","display_name":"ATD: Sparsity Models for Forecasting Spatio-Temporal Human Dynamics","funder_award_id":"1737770","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306151","display_name":"Alfred P. Sloan Foundation","ror":"https://ror.org/052csg198"},{"id":"https://openalex.org/F4320333591","display_name":"Multidisciplinary University Research Initiative","ror":null},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2605690107.pdf","grobid_xml":"https://content.openalex.org/works/W2605690107.grobid-xml"},"referenced_works_count":67,"referenced_works":["https://openalex.org/W41404523","https://openalex.org/W46452414","https://openalex.org/W59220370","https://openalex.org/W109869499","https://openalex.org/W140599620","https://openalex.org/W1480376833","https://openalex.org/W1510441499","https://openalex.org/W1532325895","https://openalex.org/W1565020018","https://openalex.org/W1586468107","https://openalex.org/W1646278814","https://openalex.org/W1660390307","https://openalex.org/W1673075472","https://openalex.org/W1880262756","https://openalex.org/W1978394996","https://openalex.org/W1989524890","https://openalex.org/W1995099886","https://openalex.org/W1996191381","https://openalex.org/W2024652123","https://openalex.org/W2027393969","https://openalex.org/W2031250218","https://openalex.org/W2034190452","https://openalex.org/W2057194219","https://openalex.org/W2065259291","https://openalex.org/W2072240081","https://openalex.org/W2076566842","https://openalex.org/W2092336114","https://openalex.org/W2095644746","https://openalex.org/W2108087318","https://openalex.org/W2108991785","https://openalex.org/W2114933215","https://openalex.org/W2116781287","https://openalex.org/W2121893000","https://openalex.org/W2128600649","https://openalex.org/W2133626129","https://openalex.org/W2148524305","https://openalex.org/W2152311353","https://openalex.org/W2152502401","https://openalex.org/W2154785834","https://openalex.org/W2157305458","https://openalex.org/W2157468491","https://openalex.org/W2162630660","https://openalex.org/W2164456230","https://openalex.org/W2165612380","https://openalex.org/W2166733100","https://openalex.org/W2168440643","https://openalex.org/W2170674956","https://openalex.org/W2170902582","https://openalex.org/W2295789823","https://openalex.org/W2325021267","https://openalex.org/W2397013632","https://openalex.org/W2585750209","https://openalex.org/W2604123379","https://openalex.org/W2724191931","https://openalex.org/W2743084590","https://openalex.org/W2911997405","https://openalex.org/W3124682511","https://openalex.org/W3144448110","https://openalex.org/W3146259567","https://openalex.org/W4213009331","https://openalex.org/W4242911326","https://openalex.org/W4246198815","https://openalex.org/W4247832998","https://openalex.org/W4254148532","https://openalex.org/W4285719527","https://openalex.org/W4400191782","https://openalex.org/W6637101025"],"related_works":["https://openalex.org/W1984733048","https://openalex.org/W2129535348","https://openalex.org/W2250140425","https://openalex.org/W2786479229","https://openalex.org/W3122011053","https://openalex.org/W3201783519","https://openalex.org/W3203785702","https://openalex.org/W2765264756","https://openalex.org/W4286909549","https://openalex.org/W3006107134"],"abstract_inverted_index":{"We":[0,83,125,139],"consider":[1],"the":[2,31,57,81,144,154,171,177,204,221,237,244,250],"problem":[3],"of":[4,63,97,163,223,239,243,246],"duplicate":[5],"detection":[6],"in":[7,17,135,188,228,236,249],"noisy":[8,92],"and":[9,44,79,105,160,231],"incomplete":[10],"data:":[11],"Given":[12],"a":[13,68,112,240],"large":[14],"data":[15,134,152,158,251],"set":[16],"which":[18,26,47],"each":[19],"record":[20],"has":[21],"multiple":[22],"entries":[23],"(attributes),":[24],"detect":[25],"distinct":[27],"records":[28,51,74],"refer":[29],"to":[30,50,56,130,182],"same":[32,58],"real-world":[33],"entity.":[34,59],"This":[35],"task":[36],"is":[37],"complicated":[38],"by":[39],"noise":[40],"(such":[41],"as":[42,176],"misspellings)":[43],"missing":[45,133],"data,":[46],"can":[48,202],"lead":[49],"being":[52],"different,":[53],"despite":[54],"referring":[55],"Our":[60],"method":[61,142,217],"consists":[62],"three":[64],"main":[65],"steps:":[66],"creating":[67,88],"similarity":[69,89,137],"score":[70],"between":[71,91],"records,":[72,93],"grouping":[73],"together":[75],"into":[76],"\u201cunique":[77],"entities\u201d,":[78],"refining":[80],"groups.":[82],"compare":[84],"various":[85],"methods":[86,129,172,201],"for":[87,218,233],"scores":[90],"considering":[94],"different":[95],"combinations":[96],"string":[98],"matching,":[99],"term":[100,115,197,206],"frequency-inverse":[101,116,198,207],"document":[102,117,199,208],"frequency":[103,118,200,209],"methods,":[104],"n-gram":[106],"techniques.":[107],"In":[108],"particular,":[109],"we":[110],"introduce":[111],"vectorized":[113],"soft":[114,196],"method,":[119],"with":[120,132],"an":[121],"optional":[122],"refinement":[123],"step.":[124],"also":[126,213],"discuss":[127],"two":[128,161],"deal":[131],"computing":[136],"scores.":[138],"test":[140],"our":[141,216],"on":[143],"Los":[145],"Angeles":[146],"Police":[147],"Department":[148],"Field":[149],"Interview":[150],"Card":[151],"set,":[153,159],"Cora":[155],"Citation":[156],"Matching":[157],"sets":[162],"restaurant":[164],"review":[165],"data.":[166],"The":[167,211],"results":[168,212,235],"show":[169],"that":[170,173,184,215],"use":[174,185],"words":[175],"basic":[178],"units":[179],"are":[180],"preferable":[181],"those":[183],"3-grams.":[186],"Moreover,":[187],"some":[189],"(but":[190],"certainly":[191],"not":[192],"all)":[193],"parameter":[194],"ranges":[195],"outperform":[203],"standard":[205],"method.":[210],"confirm":[214],"automatically":[219],"determining":[220],"number":[222,245],"groups":[224],"typically":[225],"works":[226],"well":[227],"many":[229],"cases":[230],"allows":[232],"accurate":[234],"absence":[238],"priori":[241],"knowledge":[242],"unique":[247],"entities":[248],"set.":[252]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}