{"id":"https://openalex.org/W2002597960","doi":"https://doi.org/10.1145/2588555.2610530","title":"On-the-fly token similarity joins in relational databases","display_name":"On-the-fly token similarity joins in relational databases","publication_year":2014,"publication_date":"2014-06-18","ids":{"openalex":"https://openalex.org/W2002597960","doi":"https://doi.org/10.1145/2588555.2610530","mag":"2002597960"},"language":"en","primary_location":{"id":"doi:10.1145/2588555.2610530","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2588555.2610530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 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/A5089328860","display_name":"Nikolaus Augsten","orcid":"https://orcid.org/0000-0002-3036-6201"},"institutions":[{"id":"https://openalex.org/I182212641","display_name":"University of Salzburg","ror":"https://ror.org/05gs8cd61","country_code":"AT","type":"education","lineage":["https://openalex.org/I182212641"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Nikolaus Augsten","raw_affiliation_strings":["University of Salzburg, Salzburg, Austria"],"affiliations":[{"raw_affiliation_string":"University of Salzburg, Salzburg, Austria","institution_ids":["https://openalex.org/I182212641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083106347","display_name":"Armando Miraglia","orcid":null},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Armando Miraglia","raw_affiliation_strings":["VU University Amsterdam, Amsterdam, Netherlands","VU University Amsterdam, Amsterdam, Netherlands#TAB#"],"affiliations":[{"raw_affiliation_string":"VU University Amsterdam, Amsterdam, Netherlands","institution_ids":[]},{"raw_affiliation_string":"VU University Amsterdam, Amsterdam, Netherlands#TAB#","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101880157","display_name":"Thomas Neumann","orcid":"https://orcid.org/0000-0001-5787-142X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Neumann","raw_affiliation_strings":["TU M\u00fcnchen, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"TU M\u00fcnchen, Munich, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105817801","display_name":"Alfons Kemper","orcid":"https://orcid.org/0009-0003-9066-271X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alfons Kemper","raw_affiliation_strings":["TU M\u00fcnchen, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"TU M\u00fcnchen, Munich, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089328860"],"corresponding_institution_ids":["https://openalex.org/I182212641"],"apc_list":null,"apc_paid":null,"fwci":2.0291,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.87182544,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1495","last_page":"1506"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9954000115394592,"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/T11106","display_name":"Data Management and Algorithms","score":0.994700014591217,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.8731920719146729},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8142223358154297},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.6780998706817627},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.6484856605529785},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6363442540168762},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5959177017211914},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5397317409515381},{"id":"https://openalex.org/keywords/relational-calculus","display_name":"Relational calculus","score":0.461150199174881},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.44581910967826843},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37856993079185486},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34821927547454834},{"id":"https://openalex.org/keywords/relational-model","display_name":"Relational model","score":0.20828962326049805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19128340482711792},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.139278382062912}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.8731920719146729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8142223358154297},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.6780998706817627},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.6484856605529785},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6363442540168762},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5959177017211914},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5397317409515381},{"id":"https://openalex.org/C99436015","wikidata":"https://www.wikidata.org/wiki/Q1722436","display_name":"Relational calculus","level":4,"score":0.461150199174881},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.44581910967826843},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37856993079185486},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34821927547454834},{"id":"https://openalex.org/C40207289","wikidata":"https://www.wikidata.org/wiki/Q755662","display_name":"Relational model","level":3,"score":0.20828962326049805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19128340482711792},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.139278382062912},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2588555.2610530","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2588555.2610530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1969375478","https://openalex.org/W1973535531","https://openalex.org/W1993831977","https://openalex.org/W1996186909","https://openalex.org/W2017645867","https://openalex.org/W2018312189","https://openalex.org/W2022979132","https://openalex.org/W2032338144","https://openalex.org/W2033629528","https://openalex.org/W2035835285","https://openalex.org/W2043481183","https://openalex.org/W2065259291","https://openalex.org/W2094689410","https://openalex.org/W2096598900","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2107412086","https://openalex.org/W2119057313","https://openalex.org/W2119441285","https://openalex.org/W2121269638","https://openalex.org/W2121516976","https://openalex.org/W2123020735","https://openalex.org/W2127675794","https://openalex.org/W2128793454","https://openalex.org/W2132069633","https://openalex.org/W2135888006","https://openalex.org/W2141469207","https://openalex.org/W2161936973"],"related_works":["https://openalex.org/W1487241321","https://openalex.org/W2085988990","https://openalex.org/W2005835473","https://openalex.org/W60748262","https://openalex.org/W2056340443","https://openalex.org/W4362564457","https://openalex.org/W1494193231","https://openalex.org/W2042847482","https://openalex.org/W2117881132","https://openalex.org/W2767499799"],"abstract_inverted_index":{"Token":[0],"similarity":[1,41,83,106,177],"joins":[2,42,84],"represent":[3],"data":[4],"items":[5,24],"as":[6,15,71,124],"sets":[7,16,33],"of":[8,17,20,73,126,169],"tokens,":[9,139],"for":[10,138,160,176],"example,":[11],"strings":[12],"are":[13,25,57],"represented":[14],"q-grams":[18],"(substrings":[19],"length":[21],"q).":[22],"Two":[23],"considered":[26],"similar":[27],"and":[28,64,103,155,171],"match":[29],"if":[30],"their":[31],"token":[32,66,82,122],"have":[34],"a":[35,96],"large":[36],"overlap.":[37],"Previous":[38],"work":[39],"on":[40,47,145],"in":[43,61,166],"databases":[44],"mainly":[45],"focuses":[46],"expressing":[48],"the":[49,62,65,74,105,121,127,132,146,167],"overlap":[50],"computation":[51],"with":[52,135],"relational":[53,98,113],"operators.":[54],"The":[55],"tokens":[56,90,102],"assumed":[58],"to":[59,79,108,118],"preexist":[60],"database,":[63],"generation":[67,123],"cannot":[68],"be":[69,109],"expressed":[70],"part":[72,125],"query.":[75],"Our":[76],"goal":[77],"is":[78],"efficiently":[80],"compute":[81],"on-the-fly,":[85],"i.e.,":[86],"without":[87],"any":[88],"precomputed":[89],"or":[91],"indexes.":[92],"We":[93,149,162],"define":[94],"tokenize,":[95],"new":[97],"operator":[99,165],"that":[100],"generates":[101],"allows":[104,116],"join":[107],"fully":[110],"integrated":[111],"into":[112],"databases.":[114],"This":[115],"us":[117],"(1)":[119],"optimize":[120],"query":[128,133,147],"plan,":[129],"(2)":[130],"provide":[131],"optimizer":[134],"cardinality":[136,153],"estimates":[137],"(3)":[140],"choose":[141],"efficient":[142,157],"algorithms":[143],"based":[144],"context.":[148],"discuss":[150],"algebraic":[151],"properties,":[152],"estimates,":[154],"an":[156],"iterator":[158],"algorithm":[159],"tokenize.":[161],"implemented":[163],"our":[164],"kernel":[168],"PostgreSQL":[170],"empirically":[172],"evaluated":[173],"its":[174],"performance":[175],"joins.":[178]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}