{"id":"https://openalex.org/W2054693333","doi":"https://doi.org/10.1145/1807167.1807204","title":"Probabilistic string similarity joins","display_name":"Probabilistic string similarity joins","publication_year":2010,"publication_date":"2010-06-06","ids":{"openalex":"https://openalex.org/W2054693333","doi":"https://doi.org/10.1145/1807167.1807204","mag":"2054693333"},"language":"en","primary_location":{"id":"doi:10.1145/1807167.1807204","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD 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/A5064482744","display_name":"Jeffrey Jestes","orcid":null},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jeffrey Jestes","raw_affiliation_strings":["Florida State University, Tallahassee, FL, USA","Florida State University , Tallahassee , FL , USA"],"affiliations":[{"raw_affiliation_string":"Florida State University, Tallahassee, FL, USA","institution_ids":["https://openalex.org/I103163165"]},{"raw_affiliation_string":"Florida State University , Tallahassee , FL , USA","institution_ids":["https://openalex.org/I103163165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450470","display_name":"Feifei Li","orcid":"https://orcid.org/0009-0003-0770-5775"},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feifei Li","raw_affiliation_strings":["Florida State University, Tallahassee, FL, USA","Florida State University , Tallahassee , FL , USA"],"affiliations":[{"raw_affiliation_string":"Florida State University, Tallahassee, FL, USA","institution_ids":["https://openalex.org/I103163165"]},{"raw_affiliation_string":"Florida State University , Tallahassee , FL , USA","institution_ids":["https://openalex.org/I103163165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040622494","display_name":"Zhepeng Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhepeng Yan","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong","Hong Kong University Of Science And Technology, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Hong Kong University Of Science And Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009196125","display_name":"Ke Yi","orcid":"https://orcid.org/0000-0002-2178-3716"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ke Yi","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong","Hong Kong University Of Science And Technology, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Hong Kong University Of Science And Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064482744"],"corresponding_institution_ids":["https://openalex.org/I103163165"],"apc_list":null,"apc_paid":null,"fwci":7.6547,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.97166557,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"327","last_page":"338"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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":0.9861999750137329,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.965399980545044,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.7773184776306152},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.7551264762878418},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.7383742332458496},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6840985417366028},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6660705804824829},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.6069519519805908},{"id":"https://openalex.org/keywords/probabilistic-database","display_name":"Probabilistic database","score":0.5290210247039795},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5201485753059387},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"Approximate string matching","score":0.5192030072212219},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.496326744556427},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4791371524333954},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.43066102266311646},{"id":"https://openalex.org/keywords/string-kernel","display_name":"String kernel","score":0.4235600233078003},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3954973518848419},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.31723517179489136},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.3146069645881653},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2873079180717468},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.26814210414886475},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20428967475891113},{"id":"https://openalex.org/keywords/database-theory","display_name":"Database theory","score":0.183088481426239},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.137364000082016},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.07450300455093384}],"concepts":[{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.7773184776306152},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.7551264762878418},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.7383742332458496},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6840985417366028},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6660705804824829},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.6069519519805908},{"id":"https://openalex.org/C174539288","wikidata":"https://www.wikidata.org/wiki/Q7246853","display_name":"Probabilistic database","level":4,"score":0.5290210247039795},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5201485753059387},{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.5192030072212219},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.496326744556427},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4791371524333954},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.43066102266311646},{"id":"https://openalex.org/C55851704","wikidata":"https://www.wikidata.org/wiki/Q7623983","display_name":"String kernel","level":5,"score":0.4235600233078003},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3954973518848419},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.31723517179489136},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.3146069645881653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2873079180717468},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.26814210414886475},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20428967475891113},{"id":"https://openalex.org/C12439846","wikidata":"https://www.wikidata.org/wiki/Q4809258","display_name":"Database theory","level":3,"score":0.183088481426239},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.137364000082016},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.07450300455093384},{"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"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/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1807167.1807204","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.164.4237","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.164.4237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ust.hk/~yike/sigmod10ped.pdf","raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-27428","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-27428","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":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"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":31,"referenced_works":["https://openalex.org/W1561514023","https://openalex.org/W1578664299","https://openalex.org/W1887000090","https://openalex.org/W1963853643","https://openalex.org/W2037458235","https://openalex.org/W2050507347","https://openalex.org/W2072173758","https://openalex.org/W2075187555","https://openalex.org/W2088422262","https://openalex.org/W2103747951","https://openalex.org/W2105423800","https://openalex.org/W2109402524","https://openalex.org/W2115986770","https://openalex.org/W2116440837","https://openalex.org/W2119057313","https://openalex.org/W2121516976","https://openalex.org/W2129035130","https://openalex.org/W2140757415","https://openalex.org/W2143485006","https://openalex.org/W2144562386","https://openalex.org/W2144810465","https://openalex.org/W2150916025","https://openalex.org/W2153508518","https://openalex.org/W2158779275","https://openalex.org/W2161936973","https://openalex.org/W2167847032","https://openalex.org/W3125945533","https://openalex.org/W4285719527","https://openalex.org/W6672615329","https://openalex.org/W6682435157","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":{"Edit":[0],"distance":[1,74],"based":[2],"string":[3,11,31,41,63,68,85,92],"similarity":[4,78],"join":[5,64],"is":[6,53,100,136],"a":[7,55,114],"fundamental":[8],"operator":[9],"in":[10,16,30,38,66,91,94,121,152],"databases.":[12],"Increasingly,":[13],"many":[14],"applications":[15],"data":[17,19,46,164],"cleaning,":[18],"integration,":[20],"and":[21,43,49,108,143],"scientific":[22],"computing":[23,129],"have":[24,140,165],"to":[25,87,106],"deal":[26],"with":[27],"fuzzy":[28],"information":[29],"attributes.":[32],"Despite":[33],"the":[34,62,71,77,89,130,173],"intensive":[35],"efforts":[36],"devoted":[37],"processing":[39,50],"(deterministic)":[40],"joins":[42],"managing":[44],"probabilistic":[45,51,67,84,134],"respectively,":[47],"modeling":[48],"strings":[52,122,135],"still":[54],"largely":[56],"unexplored":[57],"territory.":[58],"This":[59],"work":[60],"studies":[61],"problem":[65],"databases,":[69],"using":[70],"expected":[72],"edit":[73],"(EED)":[75],"as":[76],"measure.":[79],"We":[80],"first":[81],"discuss":[82],"two":[83,133],"models":[86],"capture":[88],"fuzziness":[90],"values":[93],"real-world":[95],"applications.":[96],"The":[97,110],"string-level":[98],"model":[99,112],"complete,":[101],"but":[102],"may":[103],"be":[104,149],"expensive":[105],"represent":[107],"process.":[109],"character-level":[111],"has":[113],"much":[115],"more":[116],"succinct":[117],"representation":[118],"when":[119],"uncertainty":[120],"only":[123],"exists":[124],"at":[125],"certain":[126],"positions.":[127],"Since":[128],"EED":[131],"between":[132],"prohibitively":[137],"expensive,":[138],"we":[139],"designed":[141],"efficient":[142],"effective":[144],"pruning":[145],"techniques":[146],"that":[147],"can":[148],"easily":[150],"implemented":[151],"existing":[153],"relational":[154],"database":[155],"engines":[156],"for":[157],"both":[158],"models.":[159],"Extensive":[160],"experiments":[161],"on":[162],"real":[163],"demonstrated":[166],"order-of-magnitude":[167],"improvements":[168],"of":[169],"our":[170],"approaches":[171],"over":[172],"baseline.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}