{"id":"https://openalex.org/W2167331726","doi":"https://doi.org/10.1007/s00778-011-0252-8","title":"Trie-join: a trie-based method for efficient string similarity joins","display_name":"Trie-join: a trie-based method for efficient string similarity joins","publication_year":2011,"publication_date":"2011-10-03","ids":{"openalex":"https://openalex.org/W2167331726","doi":"https://doi.org/10.1007/s00778-011-0252-8","mag":"2167331726"},"language":"en","primary_location":{"id":"doi:10.1007/s00778-011-0252-8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00778-011-0252-8","pdf_url":null,"source":{"id":"https://openalex.org/S78926909","display_name":"The VLDB Journal","issn_l":"0949-877X","issn":["0949-877X","1066-8888"],"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 VLDB Journal","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/A5100951661","display_name":"Jianhua Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianhua Feng","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101850961","display_name":"Jiannan Wang","orcid":"https://orcid.org/0009-0002-8978-312X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiannan Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100451576","display_name":"Guoliang Li","orcid":"https://orcid.org/0000-0002-1398-0621"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang Li","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100951661"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":null,"fwci":8.4947,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.97744285,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"21","issue":"4","first_page":"437","last_page":"461"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/trie","display_name":"Trie","score":0.9044055342674255},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.8339188694953918},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.7455389499664307},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.711484968662262},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.6579179763793945},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6513499021530151},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.604809045791626},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.5982441306114197},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5106015801429749},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.4999878406524658},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.48849165439605713},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47744303941726685},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4382967948913574},{"id":"https://openalex.org/keywords/hash-join","display_name":"Hash join","score":0.4294711947441101},{"id":"https://openalex.org/keywords/string-kernel","display_name":"String kernel","score":0.41496390104293823},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3883368968963623},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20655575394630432},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15058493614196777},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0888519287109375},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.07590803503990173}],"concepts":[{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.9044055342674255},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.8339188694953918},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.7455389499664307},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.711484968662262},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.6579179763793945},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6513499021530151},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.604809045791626},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.5982441306114197},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5106015801429749},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.4999878406524658},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.48849165439605713},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47744303941726685},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4382967948913574},{"id":"https://openalex.org/C188805328","wikidata":"https://www.wikidata.org/wiki/Q4060691","display_name":"Hash join","level":3,"score":0.4294711947441101},{"id":"https://openalex.org/C55851704","wikidata":"https://www.wikidata.org/wiki/Q7623983","display_name":"String kernel","level":5,"score":0.41496390104293823},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3883368968963623},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20655575394630432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15058493614196777},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0888519287109375},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.07590803503990173},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.0},{"id":"https://openalex.org/C160446489","wikidata":"https://www.wikidata.org/wiki/Q7226642","display_name":"Polynomial kernel","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00778-011-0252-8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00778-011-0252-8","pdf_url":null,"source":{"id":"https://openalex.org/S78926909","display_name":"The VLDB Journal","issn_l":"0949-877X","issn":["0949-877X","1066-8888"],"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 VLDB Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W57699484","https://openalex.org/W65332816","https://openalex.org/W125979907","https://openalex.org/W1500117362","https://openalex.org/W1578664299","https://openalex.org/W1585070348","https://openalex.org/W1956559956","https://openalex.org/W1974995373","https://openalex.org/W1978510388","https://openalex.org/W1993449345","https://openalex.org/W2001496424","https://openalex.org/W2021283827","https://openalex.org/W2040102554","https://openalex.org/W2040455459","https://openalex.org/W2054693333","https://openalex.org/W2064926388","https://openalex.org/W2072173758","https://openalex.org/W2076338409","https://openalex.org/W2076747312","https://openalex.org/W2085218027","https://openalex.org/W2096598900","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2098571654","https://openalex.org/W2099370490","https://openalex.org/W2103014446","https://openalex.org/W2105423800","https://openalex.org/W2105436061","https://openalex.org/W2108190694","https://openalex.org/W2111192396","https://openalex.org/W2113618143","https://openalex.org/W2114764731","https://openalex.org/W2115214414","https://openalex.org/W2115215982","https://openalex.org/W2119057313","https://openalex.org/W2121516976","https://openalex.org/W2123020735","https://openalex.org/W2125980212","https://openalex.org/W2127675794","https://openalex.org/W2128160875","https://openalex.org/W2129750215","https://openalex.org/W2131815873","https://openalex.org/W2132331529","https://openalex.org/W2139660688","https://openalex.org/W2147033904","https://openalex.org/W2150916025","https://openalex.org/W2151930506","https://openalex.org/W2155512447","https://openalex.org/W2157092487","https://openalex.org/W2158779275","https://openalex.org/W2161936973","https://openalex.org/W2162102353","https://openalex.org/W2162592052","https://openalex.org/W2164501930","https://openalex.org/W2166804299","https://openalex.org/W2167847032","https://openalex.org/W2171972576","https://openalex.org/W2337480916","https://openalex.org/W4252040602","https://openalex.org/W4256160948"],"related_works":["https://openalex.org/W2727277874","https://openalex.org/W2950268498","https://openalex.org/W2298909997","https://openalex.org/W2102443632","https://openalex.org/W1505906253","https://openalex.org/W2154800282","https://openalex.org/W2073112656","https://openalex.org/W1995433548","https://openalex.org/W2756522268","https://openalex.org/W2167331726"],"abstract_inverted_index":null,"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":11}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}