{"id":"https://openalex.org/W118209581","doi":null,"title":"Towards Parameter-free Blocking for Scalable Record Linkage","display_name":"Towards Parameter-free Blocking for Scalable Record Linkage","publication_year":2007,"publication_date":"2007-08-01","ids":{"openalex":"https://openalex.org/W118209581","mag":"118209581"},"language":"en","primary_location":{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/45752","doi":null,"is_oa":true,"landing_page_url":"http://cs.anu.edu.au/techreports/2007/TR-CS-07-03.html","pdf_url":"http://hdl.handle.net/1885/45752","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Working/Technical Paper"},"volume":null,"type":"report","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1885/45752","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022945960","display_name":"Peter Christen","orcid":"https://orcid.org/0000-0003-3435-2015","observed_orcids":["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":true,"raw_author_name":"Christen, Peter","raw_affiliation_strings":["Department of Computer Science , The Australian National University Canberra ACT 0200 , Australia","Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , The Australian National University Canberra ACT 0200 , Australia","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5022945960"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-linkage","display_name":"data linkage","score":0.9929999709129333},{"id":"https://openalex.org/keywords/blocking","display_name":"blocking","score":0.6740000247955322},{"id":"https://openalex.org/keywords/database-matching","display_name":"database matching","score":0.6019999980926514},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.6179999709129333},{"id":"https://openalex.org/keywords/parameter-tuning","display_name":"parameter tuning","score":0.6439999938011169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7523558139801025},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.7123918533325195},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6262933611869812},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.6208739280700684},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6166576743125916},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5086851716041565},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5032686591148376},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4877925217151642},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48466378450393677},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.4458996653556824},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42679888010025024},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.41825687885284424},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1082649827003479},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07637473940849304},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/45752","doi":null,"is_oa":true,"landing_page_url":"http://cs.anu.edu.au/techreports/2007/TR-CS-07-03.html","pdf_url":"http://hdl.handle.net/1885/45752","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Working/Technical Paper"}],"best_oa_location":{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/45752","doi":null,"is_oa":true,"landing_page_url":"http://cs.anu.edu.au/techreports/2007/TR-CS-07-03.html","pdf_url":"http://hdl.handle.net/1885/45752","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Working/Technical Paper"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2452683303","display_name":"Investigation and Development of Parallel Large Scale Record Linkage Techniques","funder_award_id":"LP0453463","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W118209581.pdf","grobid_xml":"https://content.openalex.org/works/W118209581.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1540269031","https://openalex.org/W1597164057","https://openalex.org/W1610496399","https://openalex.org/W1967977344","https://openalex.org/W2024770506","https://openalex.org/W2036216970","https://openalex.org/W2039001182","https://openalex.org/W2039561007","https://openalex.org/W2064549288","https://openalex.org/W2073471108","https://openalex.org/W2098034668","https://openalex.org/W2102350406","https://openalex.org/W2105423800","https://openalex.org/W2111116800","https://openalex.org/W2112912553","https://openalex.org/W2128661986","https://openalex.org/W2154785834","https://openalex.org/W2161600801","https://openalex.org/W2161936973","https://openalex.org/W2167081989","https://openalex.org/W2171574281","https://openalex.org/W2223011434","https://openalex.org/W2889395214"],"related_works":["https://openalex.org/W7097395969","https://openalex.org/W2956919901","https://openalex.org/W2951882581","https://openalex.org/W2397525010","https://openalex.org/W7099527503","https://openalex.org/W7046110166","https://openalex.org/W2905135414","https://openalex.org/W2808963673","https://openalex.org/W7096036376","https://openalex.org/W2113975509"],"abstract_inverted_index":{"Linking":[0],"or":[1,22],"matching":[2],"databases":[3,35],"is":[4,36],"becoming":[5],"increasingly":[6],"important":[7],"in\\nmany":[8],"data":[9,14],"mining":[10],"projects,":[11],"as":[12,61],"linked":[13],"can":[15],"contain":[16],"information":[17],"that\\nis":[18],"not":[19],"available":[20],"otherwise,":[21],"that":[23,118],"would":[24],"be":[25,78],"too":[26],"expensive":[27],"to":[28,49,66,77,85,101,115],"collect.\\nA":[29],"main":[30],"challenge":[31],"when":[32],"linking":[33],"large":[34],"the":[37,55,81,102,107,120,123,126,140],"complexity":[38],"of":[39,72,106,125,131,142],"the\\nlinkage":[40],"process:":[41],"potentially":[42],"each":[43],"record":[44,137],"in":[45,54,83,122],"one":[46],"database":[47],"has":[48],"be\\ncompared":[50],"with":[51,68,99],"all":[52],"records":[53],"other":[56],"database.":[57],"Various":[58],"techniques,\\ncollectively":[59],"know":[60],"`blocking',":[62],"have":[63],"been":[64],"developed":[65],"deal":[67],"this\\nquadratic":[69],"complexity.":[70],"Most":[71],"these":[73],"techniques":[74,95],"require":[75],"several\\nparameters":[76],"set":[79],"by":[80],"user":[82],"order":[84],"achieve":[86],"good":[87],"results.":[88],"In\\nthis":[89],"paper":[90],"we":[91],"evaluate":[92],"six":[93],"blocking":[94],"within":[96],"a":[97,113,129],"common\\nframework":[98],"regard":[100],"number":[103],"and":[104],"quality":[105,124],"candidate\\nrecord":[108],"pairs":[109],"generated.":[110],"We":[111],"propose":[112],"modification":[114],"two":[116],"existing\\ntechniques":[117],"reduces":[119],"variance":[121],"blocking\\nresults":[127],"over":[128],"range":[130],"parameter":[132],"values,":[133],"enabling":[134],"more":[135],"robust,\\npractical":[136],"linkage":[138],"without":[139],"need":[141],"time":[143],"consuming":[144],"manual\\nparameter":[145],"tuning.":[146]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}
