{"id":"https://openalex.org/W1984057771","doi":"https://doi.org/10.1145/1516360.1516455","title":"Approximate substring selectivity estimation","display_name":"Approximate substring selectivity estimation","publication_year":2009,"publication_date":"2009-03-24","ids":{"openalex":"https://openalex.org/W1984057771","doi":"https://doi.org/10.1145/1516360.1516455","mag":"1984057771"},"language":"en","primary_location":{"id":"doi:10.1145/1516360.1516455","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1516360.1516455","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1516360.1516455","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Extending Database Technology: Advances in Database Technology","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/1516360.1516455","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081157085","display_name":"Hongrae Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hongrae Lee","raw_affiliation_strings":["University of British Columbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113567130","display_name":"Raymond T. Ng","orcid":"https://orcid.org/0000-0003-3692-8524"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Raymond T. Ng","raw_affiliation_strings":["University of British Columbia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049064713","display_name":"Kyuseok Shim","orcid":"https://orcid.org/0000-0001-8818-0963"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyuseok Shim","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7059,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.8478045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"827","last_page":"838"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9947999715805054,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9927999973297119,"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/substring","display_name":"Substring","score":0.9183132648468018},{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.7871341109275818},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7293838858604431},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6300836205482483},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5445823669433594},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.48081767559051514},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47439268231391907},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.45747092366218567},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39908894896507263},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3770058751106262},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36200129985809326},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25688862800598145},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.2373502254486084},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2004963755607605}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.9183132648468018},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.7871341109275818},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7293838858604431},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6300836205482483},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5445823669433594},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.48081767559051514},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47439268231391907},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.45747092366218567},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39908894896507263},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3770058751106262},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36200129985809326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25688862800598145},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.2373502254486084},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2004963755607605},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1516360.1516455","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1516360.1516455","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1516360.1516455","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Extending Database Technology: Advances in Database Technology","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/1516360.1516455","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1516360.1516455","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1516360.1516455","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Extending Database Technology: Advances in Database Technology","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1719920873","display_name":null,"funder_award_id":"IITA-2008-C1090-0801-0031","funder_id":"https://openalex.org/F4320321640","funder_display_name":"Ministry of Knowledge Economy"}],"funders":[{"id":"https://openalex.org/F4320321640","display_name":"Ministry of Knowledge Economy","ror":"https://ror.org/008nkqk13"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1984057771.pdf","grobid_xml":"https://content.openalex.org/works/W1984057771.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W509898","https://openalex.org/W46452414","https://openalex.org/W938539187","https://openalex.org/W1578664299","https://openalex.org/W1660390307","https://openalex.org/W1965996575","https://openalex.org/W1984629602","https://openalex.org/W1990061958","https://openalex.org/W1993831977","https://openalex.org/W2041851430","https://openalex.org/W2067566391","https://openalex.org/W2075833184","https://openalex.org/W2081193615","https://openalex.org/W2092587157","https://openalex.org/W2096598900","https://openalex.org/W2097880962","https://openalex.org/W2102462631","https://openalex.org/W2105423800","https://openalex.org/W2112064847","https://openalex.org/W2119057313","https://openalex.org/W2132069633","https://openalex.org/W2141469207","https://openalex.org/W2167439683","https://openalex.org/W2183705191","https://openalex.org/W2610179052","https://openalex.org/W6637101025","https://openalex.org/W6674576723"],"related_works":["https://openalex.org/W1989944203","https://openalex.org/W2775696757","https://openalex.org/W2012019886","https://openalex.org/W4387083800","https://openalex.org/W2091133150","https://openalex.org/W1998479724","https://openalex.org/W2136519138","https://openalex.org/W2546839375","https://openalex.org/W2945869148","https://openalex.org/W2398781203"],"abstract_inverted_index":{"We":[0],"study":[1],"the":[2,46,71,76,119],"problem":[3],"of":[4,7,51],"estimating":[5],"selectivity":[6],"approximate":[8],"substring":[9],"queries.":[10],"Its":[11],"importance":[12],"in":[13,57],"databases":[14],"is":[15,90,103],"ever":[16],"increasing":[17],"as":[18],"more":[19,21,101],"and":[20,27,34,68,112,129],"data":[22],"are":[23,28],"input":[24],"by":[25],"users":[26],"integrated":[29],"with":[30,78],"many":[31],"typographical":[32],"errors":[33],"different":[35],"spelling":[36],"conventions.":[37],"To":[38],"begin":[39],"with,":[40],"we":[41,62,117],"consider":[42],"edit":[43],"distance":[44],"for":[45,70],"similarity":[47,124],"between":[48],"a":[49,91],"pair":[50],"strings.":[52],"Based":[53],"on":[54],"information":[55],"stored":[56],"an":[58],"extended":[59],"N-gram":[60],"table,":[61],"propose":[63],"two":[64],"estimation":[65],"algorithms,":[66],"MOF":[67,89,111],"LBS":[69,105],"task.":[72],"The":[73,84],"latter":[74],"extends":[75],"former":[77],"ideas":[79],"from":[80],"set":[81],"hashing":[82],"signatures.":[83],"experimental":[85],"results":[86],"show":[87],"that":[88,94],"light-weight":[92],"algorithm":[93],"gives":[95],"fairly":[96],"accurate":[97],"estimations.":[98],"However,":[99],"if":[100],"space":[102],"available,":[104],"can":[106],"give":[107],"better":[108],"accuracy":[109],"than":[110],"other":[113,123],"baseline":[114],"methods.":[115],"Next,":[116],"extend":[118],"proposed":[120],"solution":[121],"to":[122],"predicates,":[125],"SQL":[126],"LIKE":[127],"operator":[128],"Jaccard":[130],"similarity.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}