{"id":"https://openalex.org/W2169024178","doi":"https://doi.org/10.1145/2661829.2661869","title":"Forest-Based Dynamic Sorted Neighborhood Indexing for Real-Time Entity Resolution","display_name":"Forest-Based Dynamic Sorted Neighborhood Indexing for Real-Time Entity Resolution","publication_year":2014,"publication_date":"2014-11-03","ids":{"openalex":"https://openalex.org/W2169024178","doi":"https://doi.org/10.1145/2661829.2661869","mag":"2169024178"},"language":"en","primary_location":{"id":"doi:10.1145/2661829.2661869","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2661829.2661869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","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":false,"raw_author_name":"Banda Ramadan","raw_affiliation_strings":["The Australian National University, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","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":["The Australian National University, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1787","last_page":"1790"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9280999898910522,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9208999872207642,"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/search-engine-indexing","display_name":"Search engine indexing","score":0.8836438655853271},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8151983022689819},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6890953779220581},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6798229217529297},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6504915356636047},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.6294892430305481},{"id":"https://openalex.org/keywords/database-index","display_name":"Database index","score":0.5215149521827698},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.46934306621551514},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.454049676656723},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.4310646653175354},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.31847479939460754},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14238214492797852},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13500860333442688},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07919451594352722}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8836438655853271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8151983022689819},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6890953779220581},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6798229217529297},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6504915356636047},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.6294892430305481},{"id":"https://openalex.org/C59276292","wikidata":"https://www.wikidata.org/wiki/Q580427","display_name":"Database index","level":3,"score":0.5215149521827698},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.46934306621551514},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.454049676656723},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.4310646653175354},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31847479939460754},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14238214492797852},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13500860333442688},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07919451594352722},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2661829.2661869","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2661829.2661869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/58953","is_oa":false,"landing_page_url":"http://hdl.handle.net/1885/58953","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":"Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3452703648","display_name":"Exposing the anonymous attacker: detecting identity crimes using real-time entity resolution on large dynamic databases","funder_award_id":"LP100200079","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W69311973","https://openalex.org/W87992039","https://openalex.org/W1547612978","https://openalex.org/W1782779125","https://openalex.org/W2017167478","https://openalex.org/W2024386211","https://openalex.org/W2024770506","https://openalex.org/W2044280769","https://openalex.org/W2102869387","https://openalex.org/W2139646386","https://openalex.org/W2140789797","https://openalex.org/W2166988329","https://openalex.org/W2184381445","https://openalex.org/W3045341009"],"related_works":["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/W2059878404","https://openalex.org/W2185250746","https://openalex.org/W1562055306","https://openalex.org/W2151419829"],"abstract_inverted_index":{"Real-time":[0],"entity":[1],"resolution":[2],"(ER)":[3],"is":[4,141],"the":[5,22,40,96],"process":[6],"of":[7,98,173],"matching":[8,29,106,156,184],"a":[9,18,70,152,160],"query":[10,164],"record":[11],"in":[12,17,102,163],"sub-second":[13],"time":[14],"with":[15,55,80,130,158],"records":[16],"database":[19],"that":[20,52,75,138,147],"represent":[21],"same":[23],"real-world":[24,122],"entity.":[25],"To":[26],"facilitate":[27,85],"real-time":[28,63,86,191],"on":[30,49,105,119,155],"large":[31,121,144],"databases,":[32],"appropriate":[33],"indexing":[34,45,176],"approaches":[35],"are":[36,47,59],"required":[37],"to":[38,84,94,143,187],"reduce":[39,95],"search":[41],"space.":[42],"Most":[43],"available":[44],"techniques":[46],"based":[48],"batch":[50],"algorithms":[51],"work":[53],"only":[54,159],"static":[56],"databases":[57,145],"and":[58,100,125,146,177],"not":[60],"suitable":[61],"for":[62,88],"ER.":[64],"In":[65],"this":[66],"paper,":[67],"we":[68],"propose":[69],"forest-based":[71],"sorted":[72],"neighborhood":[73],"index":[74,78,112],"uses":[76],"multiple":[77,126,149],"trees":[79,150],"different":[81],"sorting":[82],"keys":[83],"ER":[87,192],"read-most":[89],"databases.":[90],"Our":[91,166],"technique":[92],"aims":[93],"effect":[97],"errors":[99],"variations":[101],"attribute":[103],"values":[104],"quality":[107,157],"by":[108],"building":[109],"several":[110],"distinct":[111],"trees.":[113],"We":[114],"conduct":[115],"an":[116],"experimental":[117],"evaluation":[118],"two":[120],"data":[123,128,132],"sets,":[124],"synthetic":[127],"sets":[129],"various":[131],"corruption":[133],"rates.":[134],"The":[135],"results":[136],"show":[137],"our":[139],"approach":[140,167],"scalable":[142],"using":[148],"gives":[151],"noticeable":[153],"improvement":[154],"small":[161],"increase":[162],"time.":[165],"also":[168],"achieves":[169],"over":[170],"one":[171],"order":[172],"magnitude":[174],"faster":[175],"querying":[178],"times,":[179],"as":[180,182],"well":[181],"higher":[183],"accuracy,":[185],"compared":[186],"another":[188],"recently":[189],"proposed":[190],"technique.":[193]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}