{"id":"https://openalex.org/W2596610888","doi":"https://doi.org/10.1007/s11227-017-2008-8","title":"Unsupervised blocking and probabilistic parallelisation for record matching of distributed big data","display_name":"Unsupervised blocking and probabilistic parallelisation for record matching of distributed big data","publication_year":2017,"publication_date":"2017-03-16","ids":{"openalex":"https://openalex.org/W2596610888","doi":"https://doi.org/10.1007/s11227-017-2008-8","mag":"2596610888"},"language":"en","primary_location":{"id":"doi:10.1007/s11227-017-2008-8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11227-017-2008-8","pdf_url":null,"source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-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/A5090458924","display_name":"Chenxiao Dou","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chenxiao Dou","raw_affiliation_strings":["University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008402099","display_name":"Yi Cui","orcid":"https://orcid.org/0000-0003-1436-7332"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Cui","raw_affiliation_strings":["School of Software, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008497202","display_name":"Daniel Sun","orcid":"https://orcid.org/0000-0003-2342-7421"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Daniel Sun","raw_affiliation_strings":["Data61, CSIRO, Canberra, ACT, Australia","University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data61, CSIRO, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I42894916"]},{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015158455","display_name":"Raymond K. Wong","orcid":"https://orcid.org/0000-0002-9814-6029"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Raymond Wong","raw_affiliation_strings":["University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059402413","display_name":"Muhammad Atif","orcid":"https://orcid.org/0000-0002-4139-8292"},"institutions":[{"id":"https://openalex.org/I4210141271","display_name":"National Computational Infrastructure","ror":"https://ror.org/04yx6dh41","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210141271"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Muhammad Atif","raw_affiliation_strings":["National Computational Infrastructure, Canberra, ACT, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Computational Infrastructure, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I4210141271"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354142","display_name":"Guoqiang Li","orcid":"https://orcid.org/0000-0001-9005-7112"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqiang Li","raw_affiliation_strings":["School of Software, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072670483","display_name":"Rajiv Ranjan","orcid":"https://orcid.org/0000-0002-6610-1328"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rajiv Ranjan","raw_affiliation_strings":["Newcastle University, Newcastle upon Tyne, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Newcastle University, Newcastle upon Tyne, UK","institution_ids":["https://openalex.org/I84884186"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5008497202"],"corresponding_institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I31746571","https://openalex.org/I42894916"],"apc_list":{"value":3290,"currency":"USD","value_usd":3290},"apc_paid":null,"fwci":0.9575,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77770257,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"75","issue":"2","first_page":"623","last_page":"645"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9883000254631042,"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":0.9496999979019165,"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/computer-science","display_name":"Computer science","score":0.9241538047790527},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.7875038385391235},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6548225283622742},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6137808561325073},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5155608654022217},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4428214430809021},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4006245732307434},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3324342370033264},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2663675546646118},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2611238956451416},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10454228520393372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9241538047790527},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.7875038385391235},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6548225283622742},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6137808561325073},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5155608654022217},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4428214430809021},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4006245732307434},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3324342370033264},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2663675546646118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2611238956451416},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10454228520393372},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11227-017-2008-8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11227-017-2008-8","pdf_url":null,"source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W580366031","https://openalex.org/W1540269031","https://openalex.org/W1968324103","https://openalex.org/W1986017822","https://openalex.org/W1997321932","https://openalex.org/W2024770506","https://openalex.org/W2031250218","https://openalex.org/W2058733945","https://openalex.org/W2060457712","https://openalex.org/W2064099358","https://openalex.org/W2064349969","https://openalex.org/W2067566391","https://openalex.org/W2079649893","https://openalex.org/W2086207029","https://openalex.org/W2086392024","https://openalex.org/W2095644746","https://openalex.org/W2108991785","https://openalex.org/W2111116800","https://openalex.org/W2111625757","https://openalex.org/W2117974736","https://openalex.org/W2119320829","https://openalex.org/W2143124645","https://openalex.org/W2208310611","https://openalex.org/W2216499221","https://openalex.org/W2223011434","https://openalex.org/W2288790589","https://openalex.org/W2295151155","https://openalex.org/W2563121713","https://openalex.org/W2572722855","https://openalex.org/W2582955817","https://openalex.org/W2583415355","https://openalex.org/W2585642343","https://openalex.org/W3146259567","https://openalex.org/W4254788633","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W2392835431","https://openalex.org/W4206777497","https://openalex.org/W4233347783","https://openalex.org/W2910064364","https://openalex.org/W4255224757"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
