{"id":"https://openalex.org/W2017167478","doi":"https://doi.org/10.1145/2816821","title":"Dynamic Sorted Neighborhood Indexing for Real-Time Entity Resolution","display_name":"Dynamic Sorted Neighborhood Indexing for Real-Time Entity Resolution","publication_year":2015,"publication_date":"2015-10-23","ids":{"openalex":"https://openalex.org/W2017167478","doi":"https://doi.org/10.1145/2816821","mag":"2017167478"},"language":"en","primary_location":{"id":"doi:10.1145/2816821","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2816821","pdf_url":null,"source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","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/A5019675124","display_name":"Banda Ramadan","orcid":"https://orcid.org/0000-0002-0802-4109"},"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":"Banda Ramadan","raw_affiliation_strings":["Australian National University, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"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":["Australian National University, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075528828","display_name":"Huizhi Liang","orcid":"https://orcid.org/0000-0003-4408-4528"},"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":"Huizhi Liang","raw_affiliation_strings":["Australian National University, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080206968","display_name":"Ross W. Gayler","orcid":"https://orcid.org/0000-0003-4679-585X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ross W. Gayler","raw_affiliation_strings":["Veda, Melbourne, Australia","Veda, Melbourne, Australia#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Veda, Melbourne, Australia","institution_ids":[]},{"raw_affiliation_string":"Veda, Melbourne, Australia#TAB#","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019675124"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":2.4693,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.89526656,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"6","issue":"4","first_page":"1","last_page":"29"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9861999750137329,"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/T11106","display_name":"Data Management and Algorithms","score":0.9706000089645386,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8502896428108215},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.8090492486953735},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6509081721305847},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6373147368431091},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.5897922515869141},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5465930104255676},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5457134246826172},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5391661524772644},{"id":"https://openalex.org/keywords/database-index","display_name":"Database index","score":0.45140916109085083},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.42043763399124146},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.3618440330028534},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3400309085845947},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14704453945159912}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8502896428108215},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8090492486953735},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6509081721305847},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6373147368431091},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.5897922515869141},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5465930104255676},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5457134246826172},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5391661524772644},{"id":"https://openalex.org/C59276292","wikidata":"https://www.wikidata.org/wiki/Q580427","display_name":"Database index","level":3,"score":0.45140916109085083},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.42043763399124146},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.3618440330028534},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3400309085845947},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14704453945159912},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2816821","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2816821","pdf_url":null,"source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-article"},{"id":"pmh:oai:centaur.reading.ac.uk:81989","is_oa":false,"landing_page_url":"https://centaur.reading.ac.uk/view/creators/90008875.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4306402273","display_name":"CentAUR (University of Reading)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71052956","host_organization_name":"University of Reading","host_organization_lineage":["https://openalex.org/I71052956"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/98664","is_oa":false,"landing_page_url":"http://hdl.handle.net/1885/98664","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Data and Information Quality","raw_type":"Journal article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W69311973","https://openalex.org/W147771972","https://openalex.org/W1155226818","https://openalex.org/W1502916507","https://openalex.org/W1507039213","https://openalex.org/W1547556487","https://openalex.org/W1547612978","https://openalex.org/W1598618182","https://openalex.org/W1612155886","https://openalex.org/W1782779125","https://openalex.org/W1995099886","https://openalex.org/W2024386211","https://openalex.org/W2024770506","https://openalex.org/W2031250218","https://openalex.org/W2036216970","https://openalex.org/W2039789840","https://openalex.org/W2044280769","https://openalex.org/W2073471108","https://openalex.org/W2077044633","https://openalex.org/W2079656678","https://openalex.org/W2087966340","https://openalex.org/W2099117306","https://openalex.org/W2102763740","https://openalex.org/W2108991785","https://openalex.org/W2109834209","https://openalex.org/W2112912553","https://openalex.org/W2128661986","https://openalex.org/W2131967083","https://openalex.org/W2139646386","https://openalex.org/W2140789797","https://openalex.org/W2148524305","https://openalex.org/W2150228342","https://openalex.org/W2155631901","https://openalex.org/W2161694911","https://openalex.org/W2166988329","https://openalex.org/W2169024178","https://openalex.org/W2171574281","https://openalex.org/W2184381445","https://openalex.org/W2261544779","https://openalex.org/W3045341009","https://openalex.org/W4242744113","https://openalex.org/W4298072523"],"related_works":["https://openalex.org/W3014558862","https://openalex.org/W1505866794","https://openalex.org/W2527247821","https://openalex.org/W4237510188","https://openalex.org/W1973126996","https://openalex.org/W2048379072","https://openalex.org/W4301000806","https://openalex.org/W2050039288","https://openalex.org/W2143841762","https://openalex.org/W2185250746"],"abstract_inverted_index":{"Real-time":[0],"Entity":[1],"Resolution":[2],"(ER)":[3],"is":[4,90,97,121],"the":[5,21,39,55,145,175,199,243],"process":[6],"of":[7,35,83,201],"matching":[8,171,209,266,292,297],"query":[9,46,56,117,170,255,274,291],"records":[10,15,37,72,105],"in":[11,16,58,106,181,205,250,273],"subsecond":[12],"time":[13],"with":[14,54,233,268],"a":[17,33,45,68,74,107,115,136,188,270],"database":[18,40,69,108],"that":[19,41,49,102,130,139,241,258],"represent":[20],"same":[22],"real-world":[23],"entity.":[24],"Indexing":[25],"techniques":[26,222,280],"are":[27,42,50,131,195],"generally":[28],"used":[29,80,152,196],"to":[30,44,51,114,168,197,277],"efficiently":[31],"extract":[32],"set":[34],"candidate":[36],"from":[38],"similar":[43],"record,":[47,118],"and":[48,70,96,156,160,203,254,257,290],"be":[52,151],"compared":[53],"record":[57,252],"more":[59],"detail.":[60],"The":[61],"sorted":[62,94,146],"neighborhood":[63,147],"indexing":[64,142,279,289],"method,":[65,148],"which":[66,149],"sorts":[67],"compares":[71],"within":[73],"sliding":[75],"window,":[76],"has":[77],"been":[78],"successfully":[79],"for":[81,99,124,153,281],"ER":[82,101,126],"large":[84,224],"static":[85,93,159],"databases.":[86],"However,":[87],"because":[88],"it":[89],"based":[91,143],"on":[92,127,144,208,223,230,265],"arrays":[95],"designed":[98],"batch":[100],"resolves":[103],"all":[104],"rather":[109],"than":[110],"resolving":[111],"those":[112],"relating":[113],"single":[116],"this":[119],"technique":[120,138],"not":[122],"suitable":[123],"real-time":[125,154,282],"dynamic":[128,141],"databases":[129],"constantly":[132],"updated.":[133],"We":[134,164,185,217],"propose":[135,165,187],"tree-based":[137],"facilitates":[140],"can":[150],"ER,":[155,283],"investigate":[157],"both":[158,251],"adaptive":[161],"window":[162],"approaches.":[163],"an":[166],"approach":[167,285],"reduce":[169,198],"times":[172,293],"by":[173,211],"precalculating":[174],"similarities":[176],"between":[177],"attribute":[178,206],"values":[179,207],"stored":[180],"neighboring":[182],"tree":[183],"nodes.":[184],"also":[186],"multitree":[189],"solution":[190],"where":[191],"different":[192,234],"sorting":[193],"keys":[194],"effects":[200],"errors":[202],"variations":[204],"quality":[210,236,267],"building":[212],"several":[213],"distinct":[214],"index":[215,244],"trees.":[216],"experimentally":[218],"evaluate":[219],"our":[220,284],"proposed":[221],"real":[225],"datasets,":[226],"as":[227,229,242],"well":[228],"synthetic":[231],"data":[232,235],"characteristics.":[237],"Our":[238],"results":[239],"show":[240],"grows,":[245],"no":[246],"appreciable":[247],"increase":[248,272],"occurs":[249],"insertion":[253],"times,":[256],"using":[259],"multiple":[260],"trees":[261],"gives":[262],"noticeable":[263],"improvements":[264],"only":[269],"small":[271],"time.":[275],"Compared":[276],"earlier":[278],"achieves":[286],"significantly":[287],"reduced":[288],"while":[294],"maintaining":[295],"high":[296],"accuracy.":[298]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
