{"id":"https://openalex.org/W2771507595","doi":"https://doi.org/10.1631/fitee.1601347","title":"FrepJoin: an efficient partition-based algorithm for edit similarity join","display_name":"FrepJoin: an efficient partition-based algorithm for edit similarity join","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2771507595","doi":"https://doi.org/10.1631/fitee.1601347","mag":"2771507595"},"language":"en","primary_location":{"id":"doi:10.1631/fitee.1601347","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.1601347","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"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":"Frontiers of Information Technology & Electronic 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/A5089695189","display_name":"Jizhou Luo","orcid":"https://orcid.org/0000-0002-3302-3917"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210098034","display_name":"Key Laboratory of Guangdong Province","ror":"https://ror.org/00swtqp09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210098034"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ji-zhou Luo","raw_affiliation_strings":["Guangdong Key Laboratory of Popular High Performance Computers, Key Laboratory of Service Computing and Application, Shenzhen, 518000, China","School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150001, China"],"raw_orcid":"https://orcid.org/0000-0002-3302-3917","affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Popular High Performance Computers, Key Laboratory of Service Computing and Application, Shenzhen, 518000, China","institution_ids":["https://openalex.org/I4210098034"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150001, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069539054","display_name":"Shengfei Shi","orcid":"https://orcid.org/0000-0003-2932-4618"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng-fei Shi","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150001, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396652","display_name":"Hongzhi Wang","orcid":"https://orcid.org/0000-0002-7521-2871"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong-zhi Wang","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150001, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100387065","display_name":"Jianzhong Li","orcid":"https://orcid.org/0000-0002-4119-0571"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian-zhong Li","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, 150001, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5089695189"],"corresponding_institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210098034"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":0.4678,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.7111039,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"18","issue":"10","first_page":"1499","last_page":"1510"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9991000294685364,"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/edit-distance","display_name":"Edit distance","score":0.8028563857078552},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7405655384063721},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.7197696566581726},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.635643720626831},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5320051312446594},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5223016738891602},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5192359089851379},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49273255467414856},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.49154767394065857},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.4776636064052582},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4683629274368286},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32983362674713135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27414238452911377},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1562684178352356}],"concepts":[{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.8028563857078552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7405655384063721},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.7197696566581726},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.635643720626831},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5320051312446594},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5223016738891602},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5192359089851379},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49273255467414856},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.49154767394065857},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.4776636064052582},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4683629274368286},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32983362674713135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27414238452911377},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1562684178352356},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1631/fitee.1601347","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.1601347","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"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":"Frontiers of Information Technology & Electronic Engineering","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":29,"referenced_works":["https://openalex.org/W57699484","https://openalex.org/W65332816","https://openalex.org/W1534635981","https://openalex.org/W1973001156","https://openalex.org/W1982366717","https://openalex.org/W2019412213","https://openalex.org/W2065259291","https://openalex.org/W2085922539","https://openalex.org/W2096598900","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2099194763","https://openalex.org/W2099370490","https://openalex.org/W2105423800","https://openalex.org/W2121516976","https://openalex.org/W2125980212","https://openalex.org/W2127675794","https://openalex.org/W2150916025","https://openalex.org/W2151930506","https://openalex.org/W2153508518","https://openalex.org/W2158779275","https://openalex.org/W2161936973","https://openalex.org/W2167331726","https://openalex.org/W2167847032","https://openalex.org/W2169387919","https://openalex.org/W2188600765","https://openalex.org/W4256160948","https://openalex.org/W6674576723","https://openalex.org/W6682435157"],"related_works":["https://openalex.org/W3214148052","https://openalex.org/W2151692181","https://openalex.org/W3044917232","https://openalex.org/W794462722","https://openalex.org/W2029625042","https://openalex.org/W1498160656","https://openalex.org/W4248476017","https://openalex.org/W2055693471","https://openalex.org/W2007540612","https://openalex.org/W2054882906"],"abstract_inverted_index":{"String":[0],"similarity":[1],"join":[2],"(SSJ)":[3],"is":[4,85,97],"essential":[5],"for":[6,108],"many":[7],"applications":[8],"where":[9],"near-duplicate":[10],"objects":[11],"need":[12],"to":[13,55,69,87,99,103],"be":[14],"found.":[15],"This":[16],"paper":[17],"targets":[18],"SSJ":[19,89],"with":[20,75],"edit":[21,106],"distance":[22],"constraints.":[23],"The":[24,64],"existing":[25,118],"algorithms":[26],"usually":[27],"adopt":[28],"the":[29,35,45,49,91,101,117],"filter-andrefine":[30],"framework.":[31],"They":[32],"cannot":[33],"catch":[34],"dissimilarity":[36,76],"between":[37,77],"string":[38],"subsets,":[39],"and":[40],"do":[41],"not":[42],"fully":[43],"exploit":[44],"statistics":[46,102],"such":[47,62],"as":[48],"frequencies":[50],"of":[51,112],"characters.":[52],"We":[53],"investigate":[54],"develop":[56],"a":[57,109],"partition-based":[58],"algorithm":[59,84,121],"by":[60],"using":[61],"statistics.":[63],"frequency":[65],"vectors":[66],"are":[67],"used":[68],"partition":[70],"datasets":[71],"into":[72],"data":[73],"chunks":[74],"them":[78],"being":[79],"caught":[80],"easily.":[81],"A":[82,94],"novel":[83],"designed":[86],"accelerate":[88],"via":[90],"partitioned":[92],"data.":[93],"new":[95],"filter":[96],"proposed":[98],"leverage":[100],"avoid":[104],"computing":[105],"distances":[107],"noticeable":[110],"proportion":[111],"candidate":[113],"pairs":[114],"which":[115],"survive":[116],"filters.":[119],"Our":[120],"outperforms":[122],"alternative":[123],"methods":[124],"notably":[125],"on":[126],"real":[127],"datasets.":[128]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}