{"id":"https://openalex.org/W2049804814","doi":"https://doi.org/10.1109/icde.2010.5447866","title":"Efficient processing of substring match queries with inverted q-gram indexes","display_name":"Efficient processing of substring match queries with inverted q-gram indexes","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2049804814","doi":"https://doi.org/10.1109/icde.2010.5447866","mag":"2049804814"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2010.5447866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)","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/A5100327650","display_name":"Younghoon Kim","orcid":"https://orcid.org/0000-0002-3049-035X"},"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":true,"raw_author_name":"Younghoon Kim","raw_affiliation_strings":["Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038965115","display_name":"Kyoung-Gu Woo","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyoung-Gu Woo","raw_affiliation_strings":["Samsung Electronics, Seoul, Korea","Samsung Electronics, Suwon, Korea#TAB#"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics, Seoul, Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Electronics, Suwon, Korea#TAB#","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006509336","display_name":"Hyoung-Min Park","orcid":"https://orcid.org/0000-0001-7397-8286"},"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":"Hyoungmin Park","raw_affiliation_strings":["Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"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, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100327650"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":1.3486,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.80302146,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"721","last_page":"732"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9988999962806702,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9987999796867371,"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":0.998199999332428,"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/substring","display_name":"Substring","score":0.9794844388961792},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8317109942436218},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.616912841796875},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5667862892150879},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"Approximate string matching","score":0.559374213218689},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.5030509829521179},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.4954153299331665},{"id":"https://openalex.org/keywords/regular-expression","display_name":"Regular expression","score":0.47709187865257263},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.44830384850502014},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34581732749938965},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.27763381600379944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23982959985733032},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.2258823812007904},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15194359421730042},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13907736539840698},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.054997533559799194}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.9794844388961792},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8317109942436218},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.616912841796875},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5667862892150879},{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.559374213218689},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.5030509829521179},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.4954153299331665},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.47709187865257263},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.44830384850502014},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34581732749938965},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27763381600379944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23982959985733032},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2258823812007904},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15194359421730042},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13907736539840698},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.054997533559799194},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icde.2010.5447866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W24864192","https://openalex.org/W125979907","https://openalex.org/W1512840853","https://openalex.org/W1581875405","https://openalex.org/W1660390307","https://openalex.org/W1965996575","https://openalex.org/W1983437400","https://openalex.org/W1984351882","https://openalex.org/W1984629602","https://openalex.org/W2001496424","https://openalex.org/W2011106203","https://openalex.org/W2027976416","https://openalex.org/W2041851430","https://openalex.org/W2065472179","https://openalex.org/W2066636486","https://openalex.org/W2075833184","https://openalex.org/W2083113964","https://openalex.org/W2087475263","https://openalex.org/W2087721273","https://openalex.org/W2096598900","https://openalex.org/W2097776316","https://openalex.org/W2097880962","https://openalex.org/W2105423800","https://openalex.org/W2121516976","https://openalex.org/W2123020735","https://openalex.org/W2132069633","https://openalex.org/W2138662031","https://openalex.org/W2147107544","https://openalex.org/W2150916025","https://openalex.org/W2161936973","https://openalex.org/W2167439683","https://openalex.org/W2341744633","https://openalex.org/W4246225718","https://openalex.org/W6601045156","https://openalex.org/W6605088862","https://openalex.org/W6634858684","https://openalex.org/W6641571856","https://openalex.org/W6674576723","https://openalex.org/W6674621452","https://openalex.org/W6679663036","https://openalex.org/W6683401941","https://openalex.org/W6684720995"],"related_works":["https://openalex.org/W52396946","https://openalex.org/W2298204719","https://openalex.org/W1564013439","https://openalex.org/W2395807140","https://openalex.org/W1492858093","https://openalex.org/W2902482624","https://openalex.org/W3112977702","https://openalex.org/W2376315482","https://openalex.org/W2366227422","https://openalex.org/W2218650848"],"abstract_inverted_index":{"With":[0],"the":[1,4,13,63,101,121,150],"widespread":[2],"of":[3,15,45,55,104,108],"internet,":[5],"text-based":[6],"data":[7,36],"sources":[8],"have":[9,51,73],"become":[10],"ubiquitous":[11],"and":[12,123],"demand":[14],"effective":[16],"support":[17,62],"for":[18,110,130],"string":[19,35],"matching":[20,40,48,82,112,132],"queries":[21,83,113],"becomes":[22],"ever":[23],"increasing.":[24],"The":[25],"relational":[26],"query":[27,141],"language":[28],"SQL":[29],"also":[30],"supports":[31],"LIKE":[32,64],"clause":[33,65],"over":[34],"to":[37,43,61,79,149],"handle":[38],"substring":[39,47,81,111,131],"queries.":[41,133],"Due":[42],"popularity":[44],"such":[46,86],"queries,":[49],"there":[50],"been":[52,74],"a":[53],"lot":[54],"study":[56,135],"on":[57,127],"designing":[58],"efficient":[59],"indexes":[60,72,87,146],"in":[66],"SQL.":[67],"Among":[68],"them,":[69],"q-gram":[70,145],"based":[71,126],"studied":[75],"extensively.":[76],"However,":[77],"how":[78],"process":[80],"efficiently":[84],"with":[85,144],"has":[88],"received":[89],"very":[90],"little":[91],"attention":[92],"until":[93],"recently.":[94],"In":[95],"this":[96],"paper,":[97],"we":[98,119],"show":[99],"that":[100,137],"optimal":[102,122],"execution":[103,142],"intersecting":[105],"posting":[106],"lists":[107],"q-grams":[109],"should":[114],"be":[115],"decided":[116],"judiciously.":[117],"Then":[118],"present":[120],"approximate":[124],"algorithms":[125],"cost":[128],"estimation":[129],"Performance":[134],"confirms":[136],"our":[138],"techniques":[139],"improve":[140],"time":[143],"significantly":[147],"compared":[148],"traditional":[151],"algorithms.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}