{"id":"https://openalex.org/W2143683307","doi":"https://doi.org/10.1186/1472-6947-2-9","title":"Preparation of name and address data for record linkage using hidden Markov models","display_name":"Preparation of name and address data for record linkage using hidden Markov models","publication_year":2002,"publication_date":"2002-12-13","ids":{"openalex":"https://openalex.org/W2143683307","doi":"https://doi.org/10.1186/1472-6947-2-9","mag":"2143683307","pmid":"https://pubmed.ncbi.nlm.nih.gov/12482326"},"language":"en","primary_location":{"id":"doi:10.1186/1472-6947-2-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1472-6947-2-9","pdf_url":"https://bmcmedinformdecismak.biomedcentral.com/counter/pdf/10.1186/1472-6947-2-9","source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Medical Informatics and Decision Making","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcmedinformdecismak.biomedcentral.com/counter/pdf/10.1186/1472-6947-2-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001660426","display_name":"Tim Churches","orcid":"https://orcid.org/0000-0002-7905-5877"},"institutions":[{"id":"https://openalex.org/I1311436738","display_name":"New South Wales Department of Health","ror":"https://ror.org/03tb4gf50","country_code":"AU","type":"government","lineage":["https://openalex.org/I1311436738","https://openalex.org/I2801351115"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Tim Churches","raw_affiliation_strings":["Centre for Epidemiology and Research, Public Health Division, New South Wales Department of Health, Locked Mail Bag 961, North Sydney 2059, Australia. tchur@doh.health.nsw.gov.au","Centre for Epidemiology and Research, Public Health Division, New South Wales Department of Health, North Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Epidemiology and Research, Public Health Division, New South Wales Department of Health, Locked Mail Bag 961, North Sydney 2059, Australia. tchur@doh.health.nsw.gov.au","institution_ids":["https://openalex.org/I1311436738"]},{"raw_affiliation_string":"Centre for Epidemiology and Research, Public Health Division, New South Wales Department of Health, North Sydney, Australia","institution_ids":["https://openalex.org/I1311436738"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022945960","display_name":"Peter Christen","orcid":"https://orcid.org/0000-0003-3435-2015"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Peter Christen","raw_affiliation_strings":["Department of Computer Science, Australian National University, Canberra, Australia","\u2021 Department of Computer Science, Australian National University, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"\u2021 Department of Computer Science, Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108936831","display_name":"Kim Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I1311436738","display_name":"New South Wales Department of Health","ror":"https://ror.org/03tb4gf50","country_code":"AU","type":"government","lineage":["https://openalex.org/I1311436738","https://openalex.org/I2801351115"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Kim Lim","raw_affiliation_strings":["Centre for Epidemiology and Research, Public Health Division, New South Wales Department of Health, Locked Mail Bag 961, North Sydney, 2059, Australia","Centre for Epidemiology and Research, Public Health Division, New South Wales Department of Health, North Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Epidemiology and Research, Public Health Division, New South Wales Department of Health, Locked Mail Bag 961, North Sydney, 2059, Australia","institution_ids":["https://openalex.org/I1311436738"]},{"raw_affiliation_string":"Centre for Epidemiology and Research, Public Health Division, New South Wales Department of Health, North Sydney, Australia","institution_ids":["https://openalex.org/I1311436738"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082932348","display_name":"Justin Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Justin Xi Zhu","raw_affiliation_strings":["Department of Computer Science, Australian National University, Canberra, Australia","\u2021 Department of Computer Science, Australian National University, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"\u2021 Department of Computer Science, Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5001660426"],"corresponding_institution_ids":["https://openalex.org/I1311436738"],"apc_list":{"value":1570,"currency":"GBP","value_usd":1925},"apc_paid":{"value":1570,"currency":"GBP","value_usd":1925},"fwci":5.0859,"has_fulltext":true,"cited_by_count":107,"citation_normalized_percentile":{"value":0.95456978,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"2","issue":"1","first_page":"9","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9283000230789185,"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":0.9283000230789185,"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/T12790","display_name":"Nursing Diagnosis and Documentation","score":0.017400000244379044,"subfield":{"id":"https://openalex.org/subfields/2910","display_name":"Issues, ethics and legal aspects"},"field":{"id":"https://openalex.org/fields/29","display_name":"Nursing"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10350","display_name":"Electronic Health Records Systems","score":0.011699999682605267,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8292152881622314},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.638216495513916},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.582073986530304},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5694923996925354},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5388004779815674},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.5244163274765015},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5002129077911377},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4861835837364197},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.44417673349380493},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44338318705558777},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4389108419418335},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3735053241252899},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34829914569854736},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.10765218734741211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8292152881622314},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.638216495513916},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.582073986530304},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5694923996925354},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5388004779815674},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.5244163274765015},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5002129077911377},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4861835837364197},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.44417673349380493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44338318705558777},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4389108419418335},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3735053241252899},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34829914569854736},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.10765218734741211},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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},{"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D003625","descriptor_name":"Data Collection","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D003625","descriptor_name":"Data Collection","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D003625","descriptor_name":"Data Collection","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D003625","descriptor_name":"Data Collection","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D003625","descriptor_name":"Data Collection","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D003625","descriptor_name":"Data Collection","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D003661","descriptor_name":"Decision Support Techniques","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003661","descriptor_name":"Decision Support Techniques","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003661","descriptor_name":"Decision Support Techniques","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008490","descriptor_name":"Medical Informatics","qualifier_ui":"Q000639","qualifier_name":"trends","is_major_topic":false},{"descriptor_ui":"D008490","descriptor_name":"Medical Informatics","qualifier_ui":"Q000639","qualifier_name":"trends","is_major_topic":false},{"descriptor_ui":"D008490","descriptor_name":"Medical Informatics","qualifier_ui":"Q000639","qualifier_name":"trends","is_major_topic":false},{"descriptor_ui":"D008498","descriptor_name":"Medical Record Linkage","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D008498","descriptor_name":"Medical Record Linkage","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D008498","descriptor_name":"Medical Record Linkage","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D012986","descriptor_name":"Software Validation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012986","descriptor_name":"Software Validation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012986","descriptor_name":"Software Validation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1186/1472-6947-2-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1472-6947-2-9","pdf_url":"https://bmcmedinformdecismak.biomedcentral.com/counter/pdf/10.1186/1472-6947-2-9","source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Medical Informatics and Decision Making","raw_type":"journal-article"},{"id":"pmid:12482326","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12482326","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC medical informatics and decision making","raw_type":null},{"id":"pmh:oai:doaj.org/article:7526ed0a2d374b568cc72f3c88e98c0f","is_oa":true,"landing_page_url":"https://doaj.org/article/7526ed0a2d374b568cc72f3c88e98c0f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Medical Informatics and Decision Making, Vol 2, Iss 1, p 9 (2002)","raw_type":"article"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:10440/248","is_oa":true,"landing_page_url":"http://hdl.handle.net/10440/248","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.biomedcentral.com/content/pdf/1472-6947-2-9.pdf","raw_type":"Journal article"},{"id":"pmh:oai:pubmedcentral.nih.gov:140019","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/140019","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Med Inform Decis Mak","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1472-6947-2-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1472-6947-2-9","pdf_url":"https://bmcmedinformdecismak.biomedcentral.com/counter/pdf/10.1186/1472-6947-2-9","source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Medical Informatics and Decision Making","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.6899999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320431","display_name":"Australian National University","ror":"https://ror.org/019wvm592"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2143683307.pdf","grobid_xml":"https://content.openalex.org/works/W2143683307.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1560013842","https://openalex.org/W1568339100","https://openalex.org/W1610496399","https://openalex.org/W1934019294","https://openalex.org/W1973578915","https://openalex.org/W2029873015","https://openalex.org/W2049633694","https://openalex.org/W2066856237","https://openalex.org/W2087211004","https://openalex.org/W2125838338","https://openalex.org/W2139585610","https://openalex.org/W2140327372","https://openalex.org/W2142384583","https://openalex.org/W2143349571","https://openalex.org/W2144564994","https://openalex.org/W2145691535","https://openalex.org/W2145948275","https://openalex.org/W2158749079","https://openalex.org/W2162340487","https://openalex.org/W2163918411","https://openalex.org/W2171850596","https://openalex.org/W2314321414","https://openalex.org/W2318728285","https://openalex.org/W2325591497","https://openalex.org/W2327544637","https://openalex.org/W4242494132","https://openalex.org/W4246425068","https://openalex.org/W6633431331"],"related_works":["https://openalex.org/W2784199898","https://openalex.org/W2487032012","https://openalex.org/W2211355040","https://openalex.org/W2808916796","https://openalex.org/W3088855600","https://openalex.org/W2176311362","https://openalex.org/W3012491082","https://openalex.org/W2024018837","https://openalex.org/W3211905090","https://openalex.org/W1936317645"],"abstract_inverted_index":{"BACKGROUND:":[0],"Record":[1],"linkage":[2,33],"refers":[3],"to":[4,12,59,66,81,90,99,117,140,152,205,222,255],"the":[5,13,25,35,136,224,238],"process":[6],"of":[7,27,37,39,46,104,129,135,148,226],"joining":[8],"records":[9],"that":[10,141],"relate":[11],"same":[14],"entity":[15],"or":[16,20,167],"event":[17],"in":[18,64,241],"one":[19],"more":[21,210],"data":[22,42,75,124,131,214,231],"collections.":[23,132],"In":[24],"absence":[26],"a":[28,102,127,172,200],"shared,":[29],"unique":[30],"key,":[31],"record":[32],"involves":[34],"comparison":[36],"ensembles":[38],"partially-identifying,":[40],"non-unique":[41],"items":[43,49],"between":[44],"pairs":[45],"records.":[47],"Data":[48],"with":[50,182,229],"variable":[51],"formats,":[52],"such":[53,215,232],"as":[54,91,216,233],"names":[55],"and":[56,62,107,122,155,197,202,257],"addresses,":[57,163],"need":[58],"be":[60,153],"transformed":[61],"normalised":[63],"order":[65],"validly":[67],"carry":[68,82],"out":[69,83],"these":[70],"comparisons.":[71],"Traditionally,":[72],"deterministic":[73],"rule-based":[74,144,174,206],"processing":[76],"systems":[77,207],"have":[78],"been":[79],"used":[80,181],"this":[84,189,227,242],"pre-processing,":[85],"which":[86,236],"is":[87,220,244],"commonly":[88],"referred":[89],"\"standardisation\".":[92],"This":[93],"paper":[94,243],"describes":[95],"an":[96,248],"alternative":[97,204],"approach":[98,228],"standardisation,":[100],"using":[101],"combination":[103],"lexicon-based":[105],"tokenisation":[106,196],"probabilistic":[108],"hidden":[109],"Markov":[110],"models":[111],"(HMMs).":[112],"METHODS:":[113],"HMMs":[114,149,164,198],"were":[115],"trained":[116],"standardise":[118],"typical":[119],"Australian":[120],"name":[121,184],"address":[123],"drawn":[125],"from":[126],"range":[128],"health":[130],"The":[133],"accuracy":[134,170,177],"results":[137],"was":[138,150,178],"compared":[139],"produced":[142,165],"by":[143],"systems.":[145],"RESULTS:":[146],"Training":[147],"found":[151],"quick":[154],"did":[156],"not":[157],"require":[158],"any":[159],"specialised":[160],"skills.":[161],"For":[162],"equal":[166],"better":[168],"standardisation":[169],"than":[171],"widely-used":[173],"system.":[175],"However,":[176],"worse":[179],"when":[180],"simpler":[183,230],"data.":[185],"Possible":[186],"reasons":[187],"for":[188,208,252],"poorer":[190],"performance":[191,225],"are":[192],"discussed.":[193],"CONCLUSION:":[194],"Lexicon-based":[195],"provide":[199],"viable":[201],"effort-effective":[203],"pre-processing":[209],"complex":[211],"variably":[212],"formatted":[213],"addresses.":[217],"Further":[218],"work":[219],"required":[221],"improve":[223],"names.":[234],"Software":[235],"implements":[237],"methods":[239],"described":[240],"freely":[245],"available":[246],"under":[247],"open":[249],"source":[250],"license":[251],"other":[253],"researchers":[254],"use":[256],"improve.":[258]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":6}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
