{"id":"https://openalex.org/W2430378630","doi":"https://doi.org/10.1145/2882903.2915211","title":"Local Similarity Search for Unstructured Text","display_name":"Local Similarity Search for Unstructured Text","publication_year":2016,"publication_date":"2016-06-16","ids":{"openalex":"https://openalex.org/W2430378630","doi":"https://doi.org/10.1145/2882903.2915211","mag":"2430378630"},"language":"en","primary_location":{"id":"doi:10.1145/2882903.2915211","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2882903.2915211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","raw_type":"proceedings-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/A5060015507","display_name":"Pei Wang","orcid":"https://orcid.org/0000-0001-7042-9281"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Pei Wang","raw_affiliation_strings":["Nagoya University, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036148682","display_name":"Chuan Xiao","orcid":"https://orcid.org/0000-0001-7239-5134"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chuan Xiao","raw_affiliation_strings":["Nagoya University, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048552211","display_name":"Jianbin Qin","orcid":"https://orcid.org/0000-0002-4298-3215"},"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":"Jianbin Qin","raw_affiliation_strings":["The University of New South Wales, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"The University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392089","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-8180-2886"},"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":"Wei Wang","raw_affiliation_strings":["The University of New South Wales, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"The University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103049042","display_name":"Xiaoyang Zhang","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":"Xiaoyang Zhang","raw_affiliation_strings":["The University of New South Wales, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"The University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108249173","display_name":"Yoshiharu Ishikawa","orcid":"https://orcid.org/0000-0003-1368-7684"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiharu Ishikawa","raw_affiliation_strings":["Nagoya University, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5060015507"],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":3.2315,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.92233919,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1991","last_page":"2005"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9976999759674072,"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/T10028","display_name":"Topic Modeling","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/security-token","display_name":"Security token","score":0.8346573710441589},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8281165361404419},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5944448113441467},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.5605474710464478},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5379453897476196},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5090650916099548},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4949344992637634},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4639226198196411},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4514065682888031},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4452645182609558},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4246475398540497},{"id":"https://openalex.org/keywords/full-text-search","display_name":"Full text search","score":0.42331552505493164},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4184896647930145},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.26904553174972534},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26834726333618164},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2185341715812683},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08960539102554321},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08343738317489624}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8346573710441589},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8281165361404419},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5944448113441467},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.5605474710464478},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5379453897476196},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5090650916099548},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4949344992637634},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4639226198196411},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4514065682888031},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4452645182609558},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4246475398540497},{"id":"https://openalex.org/C20228898","wikidata":"https://www.wikidata.org/wiki/Q83540","display_name":"Full text search","level":3,"score":0.42331552505493164},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4184896647930145},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.26904553174972534},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26834726333618164},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2185341715812683},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08960539102554321},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08343738317489624},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2882903.2915211","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2882903.2915211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-158457","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-158457","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W120868463","https://openalex.org/W1502916507","https://openalex.org/W1531280030","https://openalex.org/W1557940919","https://openalex.org/W1609518033","https://openalex.org/W1973001156","https://openalex.org/W1974995373","https://openalex.org/W1990947147","https://openalex.org/W1991175610","https://openalex.org/W1999916788","https://openalex.org/W2003684739","https://openalex.org/W2007842132","https://openalex.org/W2019412213","https://openalex.org/W2031637148","https://openalex.org/W2044312046","https://openalex.org/W2065259291","https://openalex.org/W2067432306","https://openalex.org/W2096598900","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2098571654","https://openalex.org/W2101850236","https://openalex.org/W2109803107","https://openalex.org/W2111295912","https://openalex.org/W2113618143","https://openalex.org/W2119455368","https://openalex.org/W2121269638","https://openalex.org/W2121516976","https://openalex.org/W2127675794","https://openalex.org/W2128056631","https://openalex.org/W2132069633","https://openalex.org/W2137242774","https://openalex.org/W2148578434","https://openalex.org/W2152565070","https://openalex.org/W2156855109","https://openalex.org/W2166400748","https://openalex.org/W2167302605","https://openalex.org/W2167847032","https://openalex.org/W6629956336","https://openalex.org/W6636190696","https://openalex.org/W6674576723","https://openalex.org/W6679663036"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W2967478618","https://openalex.org/W2997152889","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W4307309205","https://openalex.org/W4288261899","https://openalex.org/W2132792521","https://openalex.org/W4254179602"],"abstract_inverted_index":{"With":[0],"the":[1,29,82,128,155,163,181,185,193],"growing":[2],"popularity":[3],"of":[4,31,62,139,142,154,195],"electronic":[5],"documents,":[6,50,92],"replication":[7],"can":[8],"occur":[9],"for":[10,79,132],"many":[11],"reasons.":[12],"People":[13],"may":[14],"copy":[15],"text":[16],"segments":[17],"from":[18],"various":[19],"sources":[20],"and":[21,123,131,171],"make":[22],"modifications.":[23],"In":[24,115,177],"this":[25],"paper,":[26],"we":[27,126,135,179],"study":[28],"problem":[30,74],"local":[32],"similarity":[33,44,95],"search":[34,45],"to":[35,54,84,109,117,149,161,168,183],"find":[36,47,150],"partially":[37],"replicated":[38],"text.":[39],"Unlike":[40],"existing":[41],"studies":[42],"on":[43,105,189],"which":[46,65],"entirely":[48],"duplicated":[49],"our":[51,196],"target":[52],"is":[53,75,103,147],"identify":[55],"documents":[56],"that":[57],"approximately":[58],"share":[59,169],"a":[60,119,151],"pair":[61],"sliding":[63,80],"windows":[64,81,167],"differ":[66],"by":[67],"no":[68],"more":[69],"than":[70,90],"\u03c4":[71],"tokens.":[72,143],"Our":[73,100],"technically":[76],"challenging":[77],"because":[78],"tokens":[83],"be":[85],"indexed":[86],"are":[87],"less":[88,98],"selective":[89],"entire":[91],"rendering":[93],"set":[94],"join-based":[96],"algorithms":[97],"efficient.":[99],"proposed":[101],"method":[102,197],"based":[104],"enumerating":[106],"token":[107,129,156],"combinations":[108,137],"obtain":[110],"signatures":[111],"with":[112],"high":[113],"selectivity.":[114],"order":[116],"strike":[118],"balance":[120],"between":[121,165],"signature":[122],"candidate":[124],"generation,":[125],"partition":[127],"universe":[130],"different":[133,140],"partitions":[134],"generate":[136],"composed":[138],"numbers":[141],"A":[144],"cost-aware":[145],"algorithm":[146],"devised":[148],"good":[152],"partitioning":[153],"universe.":[157],"We":[158],"also":[159],"propose":[160],"leverage":[162],"overlap":[164],"adjacent":[166],"computation":[170],"thus":[172],"speed":[173],"up":[174],"query":[175],"processing.":[176],"addition,":[178],"develop":[180],"techniques":[182],"support":[184],"large":[186],"thresholds.":[187],"Experiments":[188],"real":[190],"datasets":[191],"demonstrate":[192],"efficiency":[194],"against":[198],"alternative":[199],"solutions.":[200]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}