{"id":"https://openalex.org/W2597556072","doi":"https://doi.org/10.1109/tkde.2017.2687460","title":"LS-Join: Local Similarity Join on String Collections","display_name":"LS-Join: Local Similarity Join on String Collections","publication_year":2017,"publication_date":"2017-03-25","ids":{"openalex":"https://openalex.org/W2597556072","doi":"https://doi.org/10.1109/tkde.2017.2687460","mag":"2597556072"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2017.2687460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2017.2687460","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/A5100426814","display_name":"Jiaying Wang","orcid":"https://orcid.org/0000-0002-7940-7801"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiaying Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Northeastern University, Liaoning, China","[School of Computer Science and Engineering, Northeastern University, Liaoning, China]"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"[School of Computer Science and Engineering, Northeastern University, Liaoning, China]","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079763362","display_name":"Xiaochun Yang","orcid":"https://orcid.org/0000-0002-6184-4771"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochun Yang","raw_affiliation_strings":["School of Computer Science and Engineering, Northeastern University, Liaoning, China","[School of Computer Science and Engineering, Northeastern University, Liaoning, China]"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"[School of Computer Science and Engineering, Northeastern University, Liaoning, China]","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372342","display_name":"Bin Wang","orcid":"https://orcid.org/0000-0002-2694-1023"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Northeastern University, Liaoning, China","[School of Computer Science and Engineering, Northeastern University, Liaoning, China]"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"[School of Computer Science and Engineering, Northeastern University, Liaoning, China]","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028546502","display_name":"Chengfei Liu","orcid":"https://orcid.org/0000-0003-1675-1389"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chengfei Liu","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Swinburne University of Technology, Hawthorn, Vic, Australia","[Department of Computer Science and Software Engineering, Swinburne University of Technology, Hawthorn, Vic, Australia]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Swinburne University of Technology, Hawthorn, Vic, Australia","institution_ids":["https://openalex.org/I57093077"]},{"raw_affiliation_string":"[Department of Computer Science and Software Engineering, Swinburne University of Technology, Hawthorn, Vic, Australia]","institution_ids":["https://openalex.org/I57093077"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100426814"],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":1.55,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84052126,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"29","issue":"9","first_page":"1928","last_page":"1942"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9980999827384949,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"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/substring","display_name":"Substring","score":0.9028182625770569},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.8292454481124878},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.7066864371299744},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6969279050827026},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6474502086639404},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6433472633361816},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.6400395631790161},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.6190907955169678},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5430009961128235},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5176846981048584},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.4944419860839844},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"Approximate string matching","score":0.4420815408229828},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4275624454021454},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.42614060640335083},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.2451513707637787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2388569712638855},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21381914615631104},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.10883507132530212}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.9028182625770569},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.8292454481124878},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.7066864371299744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6969279050827026},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6474502086639404},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6433472633361816},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.6400395631790161},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.6190907955169678},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5430009961128235},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5176846981048584},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.4944419860839844},{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.4420815408229828},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4275624454021454},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42614060640335083},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2451513707637787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2388569712638855},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21381914615631104},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.10883507132530212},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tkde.2017.2687460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2017.2687460","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:researchbank.swinburne.edu.au:b794af08-be6d-469c-9b45-311b4dea8e00/1","is_oa":false,"landing_page_url":"http://hdl.handle.net/1959.3/438804","pdf_url":null,"source":{"id":"https://openalex.org/S4306401157","display_name":"Swinburne Research Bank (Swinburne University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I57093077","host_organization_name":"Swinburne University of Technology","host_organization_lineage":["https://openalex.org/I57093077"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Knowledge & Data Engineering, Vol. 29, no. 9 (Sep 2017), pp. 1928-1942 ","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G2919553725","display_name":null,"funder_award_id":"ARC DP160102412","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3245575644","display_name":null,"funder_award_id":"61532021","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6095984346","display_name":null,"funder_award_id":"ARC DP140103499","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6610366909","display_name":null,"funder_award_id":"61572122","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8363617674","display_name":null,"funder_award_id":"61322208","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1520663999","https://openalex.org/W1583471564","https://openalex.org/W1973001156","https://openalex.org/W1987562803","https://openalex.org/W1992673035","https://openalex.org/W1999916788","https://openalex.org/W2011632873","https://openalex.org/W2019412213","https://openalex.org/W2040818482","https://openalex.org/W2055043387","https://openalex.org/W2055261195","https://openalex.org/W2073329022","https://openalex.org/W2087064593","https://openalex.org/W2087577316","https://openalex.org/W2097776316","https://openalex.org/W2098900423","https://openalex.org/W2099370490","https://openalex.org/W2100548092","https://openalex.org/W2115214414","https://openalex.org/W2117703483","https://openalex.org/W2119057313","https://openalex.org/W2121516976","https://openalex.org/W2129750215","https://openalex.org/W2139660688","https://openalex.org/W2148148676","https://openalex.org/W2150916025","https://openalex.org/W2157233202","https://openalex.org/W2158779275","https://openalex.org/W2161936973","https://openalex.org/W2162592052","https://openalex.org/W2166400748","https://openalex.org/W2166957282","https://openalex.org/W2167847032","https://openalex.org/W2473182694","https://openalex.org/W4236236547","https://openalex.org/W6660558136","https://openalex.org/W6677631532","https://openalex.org/W6683401941"],"related_works":["https://openalex.org/W52396946","https://openalex.org/W1982055477","https://openalex.org/W2119057313","https://openalex.org/W2061135126","https://openalex.org/W2898318433","https://openalex.org/W4248804345","https://openalex.org/W2043481183","https://openalex.org/W3167141203","https://openalex.org/W2597556072","https://openalex.org/W1990169993"],"abstract_inverted_index":{"String":[0],"similarity":[1,28,36,60,104],"join,":[2],"as":[3],"an":[4,118],"essential":[5],"operation":[6],"in":[7,19],"applications":[8],"including":[9],"data":[10,13],"integration":[11],"and":[12,67,117],"cleaning,":[14],"has":[15],"attracted":[16],"significant":[17],"attention":[18],"the":[20,75,124,138,156],"research":[21],"community.":[22],"Previous":[23],"studies":[24],"focus":[25],"on":[26,107],"global":[27],"join.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33,132],"study":[34,55,153],"local":[35,59,64,69,103,145],"join":[37,61],"with":[38],"edit":[39],"distance":[40],"constraints,":[41],"which":[42],"finds":[43],"string":[44,48],"pairs":[45,66],"from":[46],"two":[47,56,79,114,144],"collections":[49],"that":[50],"have":[51],"similar":[52,65,70,83,140,146],"substrings.":[53],"We":[54,72,97,112,148],"kinds":[57],"of":[58,93,126,158],"problems:":[62],"checking":[63],"locating":[68],"pairs.":[71,130],"first":[73],"consider":[74],"case":[76],"where":[77],"if":[78],"strings":[80],"are":[81],"locally":[82],"to":[84,100,121,136,154],"each":[85],"other,":[86],"they":[87],"must":[88],"share":[89],"a":[90,94,108,134,150],"common":[91],"gram":[92,110,129],"certain":[95],"length.":[96],"show":[98],"how":[99],"do":[101],"efficient":[102],"verification":[105],"based":[106],"matching":[109,128],"pair.":[111],"propose":[113],"pruning":[115],"techniques":[116],"incremental":[119],"method":[120,135],"further":[122],"improve":[123],"efficiency":[125,157],"finding":[127],"Then,":[131],"devise":[133],"locate":[137],"longest":[139],"substring":[141],"pair":[142],"for":[143],"strings.":[147],"conducted":[149],"comprehensive":[151],"experimental":[152],"evaluate":[155],"these":[159],"techniques.":[160]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}