{"id":"https://openalex.org/W2756522268","doi":"https://doi.org/10.1109/tkde.2017.2756932","title":"String Similarity Search: A Hash-Based Approach","display_name":"String Similarity Search: A Hash-Based Approach","publication_year":2017,"publication_date":"2017-09-26","ids":{"openalex":"https://openalex.org/W2756522268","doi":"https://doi.org/10.1109/tkde.2017.2756932","mag":"2756522268"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2017.2756932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2017.2756932","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","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/A5101579923","display_name":"Hao Wei","orcid":"https://orcid.org/0000-0003-0747-9889"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hao Wei","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-0747-9889","affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075642293","display_name":"Jeffrey Xu Yu","orcid":"https://orcid.org/0000-0002-9738-827X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jeffrey Xu Yu","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-9738-827X","affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008951824","display_name":"Can Lu","orcid":"https://orcid.org/0000-0002-7334-2875"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Can Lu","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":6.3328,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.96654546,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"30","issue":"1","first_page":"170","last_page":"184"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9986000061035156,"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/T11719","display_name":"Data Quality and Management","score":0.994700014591217,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9937999844551086,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.8199924826622009},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.7311539649963379},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.7284599542617798},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7005922198295593},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6843233108520508},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5481101870536804},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5211310982704163},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"Approximate string matching","score":0.5189235210418701},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.5162153840065002},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.4935964345932007},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.48446083068847656},{"id":"https://openalex.org/keywords/string-kernel","display_name":"String kernel","score":0.48065459728240967},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.4437282383441925},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.4253515899181366},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.4113551676273346},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3963766098022461},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3807034194469452},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.33794528245925903},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.3326956629753113},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.3056655526161194},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29122036695480347},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1972414255142212},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19004666805267334},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.1116902232170105},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08276093006134033}],"concepts":[{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.8199924826622009},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.7311539649963379},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.7284599542617798},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7005922198295593},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6843233108520508},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5481101870536804},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5211310982704163},{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.5189235210418701},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.5162153840065002},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.4935964345932007},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.48446083068847656},{"id":"https://openalex.org/C55851704","wikidata":"https://www.wikidata.org/wiki/Q7623983","display_name":"String kernel","level":5,"score":0.48065459728240967},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.4437282383441925},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.4253515899181366},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.4113551676273346},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3963766098022461},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3807034194469452},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.33794528245925903},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.3326956629753113},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3056655526161194},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29122036695480347},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1972414255142212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19004666805267334},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.1116902232170105},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08276093006134033},{"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},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tkde.2017.2756932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2017.2756932","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/132711","is_oa":false,"landing_page_url":"http://hdl.handle.net/10453/132711","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","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":39,"referenced_works":["https://openalex.org/W1595409123","https://openalex.org/W1973001156","https://openalex.org/W1987562803","https://openalex.org/W1991175610","https://openalex.org/W1991418309","https://openalex.org/W1999916788","https://openalex.org/W2019412213","https://openalex.org/W2035198268","https://openalex.org/W2050653561","https://openalex.org/W2060170830","https://openalex.org/W2065259291","https://openalex.org/W2081193615","https://openalex.org/W2096598900","https://openalex.org/W2100548092","https://openalex.org/W2103881442","https://openalex.org/W2105423800","https://openalex.org/W2112099725","https://openalex.org/W2115214414","https://openalex.org/W2117703483","https://openalex.org/W2119057313","https://openalex.org/W2121269638","https://openalex.org/W2121516976","https://openalex.org/W2123020735","https://openalex.org/W2123845384","https://openalex.org/W2124985265","https://openalex.org/W2147717514","https://openalex.org/W2148148676","https://openalex.org/W2150916025","https://openalex.org/W2158779275","https://openalex.org/W2161936973","https://openalex.org/W2166400748","https://openalex.org/W2167331726","https://openalex.org/W2430378630","https://openalex.org/W2899702797","https://openalex.org/W3123160398","https://openalex.org/W6670726752","https://openalex.org/W6674576723","https://openalex.org/W6677631532","https://openalex.org/W6683401941"],"related_works":["https://openalex.org/W2061135126","https://openalex.org/W1982055477","https://openalex.org/W2461708070","https://openalex.org/W2187092961","https://openalex.org/W2950268498","https://openalex.org/W2102443632","https://openalex.org/W1505906253","https://openalex.org/W1995433548","https://openalex.org/W2073112656","https://openalex.org/W2756522268"],"abstract_inverted_index":{"String":[0],"similarity":[1,35,68,149,204],"search":[2,36,69,150],"is":[3,42,70,82,114,239],"a":[4,77,85,96,107,208,212],"fundamental":[5],"query":[6,16,86],"that":[7,41,90],"has":[8],"been":[9],"widely":[10],"used":[11],"for":[12,95,131,202,226],"DNA":[13],"sequencing,":[14],"error-tolerant":[15],"autocompletion,":[17],"and":[18,26,52,64,140,182,199,215,230,257,267,272],"data":[19,24,27],"cleaning":[20],"needed":[21],"in":[22,76,232,285],"database,":[23],"warehouse,":[25],"mining.":[28],"In":[29,100,143],"this":[30,144],"paper,":[31,145],"we":[32,146],"study":[33,147],"string":[34,67,74,78,87,148,203,213],"based":[37],"on":[38],"edit":[39,56],"distance":[40],"supported":[43,169],"by":[44,125,170,220],"many":[45],"database":[46,79],"management":[47],"systems":[48],"such":[49,89,187],"as":[50],"Oracle":[51],"PostgreSQL.":[53],"Given":[54],"the":[55,66,101,111,118,171,176,179,183,217,233,242,259,282,289],"distance,":[57],"ed(s,":[58,91],"t),":[59],"between":[60,245],"two":[61,123,134,191,222,227,246],"strings,":[62,164],"s":[63,88,229],"t,":[65],"to":[71,84,116,175,185,211,240],"find":[72],"every":[73],"t":[75,231],"D":[80],"which":[81,165],"similar":[83],"t)":[92],"\u2264":[93],"\u03c4":[94],"given":[97],"threshold":[98],"\u03c4.":[99],"literature,":[102],"most":[103],"existing":[104,172,283],"work":[105],"takes":[106],"filter-and-verify":[108],"approach,":[109],"where":[110,151],"filter":[112,234],"step":[113],"introduced":[115],"reduce":[117],"high":[119,265],"verification":[120],"cost":[121],"of":[122,178,278],"strings":[124,152,219,228],"utilizing":[126],"an":[127],"index":[128,180,270,273],"built":[129,181],"offline":[130],"D.":[132],"The":[133,236],"up-to-date":[135],"approaches":[136,173,263,284],"are":[137,166],"prefix":[138],"filtering":[139],"local":[141],"filtering.":[142],"can":[153,161],"be":[154],"either":[155],"short":[156],"or":[157],"long.":[158],"Our":[159,261],"approach":[160],"support":[162],"long":[163],"not":[167],"well":[168],"due":[174],"size":[177,271],"time":[184,275],"build":[186],"index.":[188],"We":[189,206,248],"propose":[190],"new":[192],"hash-based":[193,251,262],"labeling":[194],"techniques,":[195],"named":[196],"OX":[197],"label":[198],"XX":[200],"label,":[201],"search.":[205],"assign":[207],"hash-label,":[209],"Hs,":[210],"s,":[214],"prune":[216],"dissimilar":[218,243],"comparing":[221],"hash-labels,":[223],"Hsand":[224],"Ht,":[225],"step.":[235],"key":[237],"idea":[238],"take":[241],"bit-patterns":[244],"hash-labels.":[247],"discuss":[249],"our":[250,286],"approaches,":[252],"address":[253],"their":[254],"pruning":[255],"power,":[256],"give":[258],"algorithms.":[260],"achieve":[264],"efficiency,":[266],"keep":[268],"its":[269],"construction":[274],"one":[276],"order":[277],"magnitude":[279],"smaller":[280],"than":[281],"experiment":[287],"at":[288],"same":[290],"time.":[291]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}