{"id":"https://openalex.org/W1978538279","doi":"https://doi.org/10.4304/jsw.9.10.2721-2731","title":"Approximate String Similarity Join using Hashing Techniques under Edit Distance Constraints","display_name":"Approximate String Similarity Join using Hashing Techniques under Edit Distance Constraints","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W1978538279","doi":"https://doi.org/10.4304/jsw.9.10.2721-2731","mag":"1978538279"},"language":"en","primary_location":{"id":"doi:10.4304/jsw.9.10.2721-2731","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jsw.9.10.2721-2731","pdf_url":null,"source":{"id":"https://openalex.org/S114141714","display_name":"Journal of Software","issn_l":"1796-217X","issn":["1796-217X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software","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/A5101558810","display_name":"Peisen Yuan","orcid":"https://orcid.org/0000-0002-5465-9949"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peisen Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083216936","display_name":"Haoyun Wang","orcid":"https://orcid.org/0000-0002-2972-2627"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoyun Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017053786","display_name":"Jianghua Che","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianghua Che","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003734781","display_name":"Shougang Ren","orcid":"https://orcid.org/0000-0002-0366-5556"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shougang Ren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100552801","display_name":"Huanliang Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huanliang Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002985662","display_name":"Dechang Pi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dechang Pi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8086,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81158391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"9","issue":"10","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9972000122070312,"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":0.9972000122070312,"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/T11478","display_name":"Caching and Content Delivery","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9959999918937683,"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/computer-science","display_name":"Computer science","score":0.9007159471511841},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.7772640585899353},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.6645634770393372},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6364353895187378},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.618021547794342},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6062753796577454},{"id":"https://openalex.org/keywords/dynamic-perfect-hashing","display_name":"Dynamic perfect hashing","score":0.49848222732543945},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.4566672146320343},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.397426962852478},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.39340710639953613},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3419933617115021},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.30130743980407715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2107521891593933},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13752838969230652},{"id":"https://openalex.org/keywords/double-hashing","display_name":"Double hashing","score":0.08649951219558716},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07304683327674866},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.06082049012184143}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9007159471511841},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.7772640585899353},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.6645634770393372},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6364353895187378},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.618021547794342},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6062753796577454},{"id":"https://openalex.org/C122907437","wikidata":"https://www.wikidata.org/wiki/Q5318999","display_name":"Dynamic perfect hashing","level":5,"score":0.49848222732543945},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.4566672146320343},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.397426962852478},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39340710639953613},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3419933617115021},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30130743980407715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2107521891593933},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13752838969230652},{"id":"https://openalex.org/C138111711","wikidata":"https://www.wikidata.org/wiki/Q478351","display_name":"Double hashing","level":4,"score":0.08649951219558716},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07304683327674866},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.06082049012184143},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4304/jsw.9.10.2721-2731","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jsw.9.10.2721-2731","pdf_url":null,"source":{"id":"https://openalex.org/S114141714","display_name":"Journal of Software","issn_l":"1796-217X","issn":["1796-217X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software","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":50,"referenced_works":["https://openalex.org/W31201067","https://openalex.org/W57699484","https://openalex.org/W65332816","https://openalex.org/W139488912","https://openalex.org/W182905090","https://openalex.org/W1541936324","https://openalex.org/W1589793985","https://openalex.org/W1647671624","https://openalex.org/W1660390307","https://openalex.org/W1736726159","https://openalex.org/W1970026646","https://openalex.org/W2001700730","https://openalex.org/W2006017015","https://openalex.org/W2012010763","https://openalex.org/W2038281398","https://openalex.org/W2044163187","https://openalex.org/W2056496968","https://openalex.org/W2073329022","https://openalex.org/W2081193615","https://openalex.org/W2082477077","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2099370490","https://openalex.org/W2104599107","https://openalex.org/W2115214414","https://openalex.org/W2121269638","https://openalex.org/W2121516976","https://openalex.org/W2123512454","https://openalex.org/W2132069633","https://openalex.org/W2147717514","https://openalex.org/W2148148676","https://openalex.org/W2150916025","https://openalex.org/W2151930506","https://openalex.org/W2161936973","https://openalex.org/W2162592052","https://openalex.org/W2170037597","https://openalex.org/W2173213060","https://openalex.org/W2341744633","https://openalex.org/W2397770138","https://openalex.org/W6602366985","https://openalex.org/W6605689662","https://openalex.org/W6607430140","https://openalex.org/W6632467642","https://openalex.org/W6635313414","https://openalex.org/W6636915900","https://openalex.org/W6650883513","https://openalex.org/W6661516099","https://openalex.org/W6668700403","https://openalex.org/W6678503669","https://openalex.org/W6682518520"],"related_works":["https://openalex.org/W2135779989","https://openalex.org/W2811247857","https://openalex.org/W2158169729","https://openalex.org/W2000284985","https://openalex.org/W2086731314","https://openalex.org/W2975588143","https://openalex.org/W1554555624","https://openalex.org/W2752074276","https://openalex.org/W2120031510","https://openalex.org/W2065169802"],"abstract_inverted_index":{"The":[0],"string":[1,10,13,64,87,101],"similarity":[2,65,88],"join,":[3],"which":[4],"is":[5,31,110,129],"employed":[6,60],"to":[7],"find":[8],"similar":[9],"pairs":[11],"from":[12],"sets,":[14],"has":[15],"received":[16],"extensive":[17],"attention":[18],"in":[19],"database":[20],"and":[21,40,96,116,132],"information":[22],"retrieval":[23],"fields.":[24],"To":[25],"this":[26,78],"problem,":[27],"the":[28,35,54,63,114,122],"filter-and-refine":[29],"framework":[30,84,109,128],"usually":[32],"adopted":[33],"by":[34],"existing":[36],"research":[37],"work":[38],"firstly,":[39],"then":[41],"various":[42],"filtering":[43],"methods":[44],"have":[45],"been":[46],"proposed.":[47],"Recently,":[48],"tree":[49],"based":[50,90],"index":[51,98],"techniques":[52,99],"with":[53,73],"edit":[55,102],"distance":[56,75,103],"constraint":[57],"are":[58],"effectively":[59],"for":[61,85],"evaluating":[62],"join.":[66],"However,":[67],"they":[68],"do":[69],"not":[70],"scale":[71],"well":[72],"large":[74],"threshold.":[76],"In":[77],"paper,":[79],"we":[80],"propose":[81],"an":[82],"efficient":[83,131],"approximate":[86],"join":[89],"on":[91],"Min-Hashing":[92],"locality":[93],"sensitive":[94],"hashing":[95],"trie-based":[97],"under":[100],"constraints.":[104],"We":[105],"show":[106],"that":[107,126],"our":[108,127],"flexible":[111],"between":[112],"trading":[113],"efficiency":[115],"performance.":[117],"An":[118],"empirical":[119],"study":[120],"using":[121],"real":[123],"datasets":[124],"demonstrates":[125],"more":[130],"scales":[133],"better.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}