{"id":"https://openalex.org/W2123020735","doi":"https://doi.org/10.1145/1376616.1376655","title":"Cost-based variable-length-gram selection for string collections to support approximate queries efficiently","display_name":"Cost-based variable-length-gram selection for string collections to support approximate queries efficiently","publication_year":2008,"publication_date":"2008-06-09","ids":{"openalex":"https://openalex.org/W2123020735","doi":"https://doi.org/10.1145/1376616.1376655","mag":"2123020735"},"language":"en","primary_location":{"id":"doi:10.1145/1376616.1376655","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1376616.1376655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 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/A5079763362","display_name":"Xiaochun Yang","orcid":"https://orcid.org/0000-0002-6184-4771"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaochun Yang","raw_affiliation_strings":["Northeastern University, Shenyang, China","Northeastern University , Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"Northeastern University , Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100630409","display_name":"Bin Wang","orcid":"https://orcid.org/0000-0002-3689-6932"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Wang","raw_affiliation_strings":["Northeastern University, Shenyang, China","Northeastern University , Shenyang, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]},{"raw_affiliation_string":"Northeastern University , Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100369885","display_name":"Chen Li","orcid":"https://orcid.org/0000-0002-8784-8148"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Li","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA","University of California Irvine, IRVINE, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"University of California Irvine, IRVINE, CA, USA#TAB#","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079763362"],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":12.2492,"has_fulltext":false,"cited_by_count":91,"citation_normalized_percentile":{"value":0.98735511,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"353","last_page":"364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9990000128746033,"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":0.9990000128746033,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9987999796867371,"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":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.829957127571106},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.7846308946609497},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.7190808653831482},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"Approximate string matching","score":0.5218302607536316},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.4400443732738495},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.43399131298065186},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.42497518658638},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.4213118553161621},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.42125651240348816},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.41667264699935913},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.4146314859390259},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35566890239715576},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.34965136647224426},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3488517999649048},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.32950887084007263},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.23390966653823853},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19938772916793823},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.17411547899246216},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.15063083171844482},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1278059482574463}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.829957127571106},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.7846308946609497},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.7190808653831482},{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.5218302607536316},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.4400443732738495},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.43399131298065186},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.42497518658638},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.4213118553161621},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42125651240348816},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.41667264699935913},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.4146314859390259},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35566890239715576},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.34965136647224426},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3488517999649048},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.32950887084007263},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.23390966653823853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19938772916793823},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.17411547899246216},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.15063083171844482},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1278059482574463},{"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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1376616.1376655","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1376616.1376655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.144.9725","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.144.9725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ics.uci.edu/~chenli/pub/sigmod08.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W125979907","https://openalex.org/W1578664299","https://openalex.org/W1603913271","https://openalex.org/W1984351882","https://openalex.org/W1993831977","https://openalex.org/W2001496424","https://openalex.org/W2007682403","https://openalex.org/W2041851430","https://openalex.org/W2075833184","https://openalex.org/W2094159338","https://openalex.org/W2096598900","https://openalex.org/W2097776316","https://openalex.org/W2097880962","https://openalex.org/W2105423800","https://openalex.org/W2107061999","https://openalex.org/W2119057313","https://openalex.org/W2121516976","https://openalex.org/W2127675794","https://openalex.org/W2161936973","https://openalex.org/W2162102353","https://openalex.org/W2167439683","https://openalex.org/W2167847032","https://openalex.org/W6683401941"],"related_works":["https://openalex.org/W2136519138","https://openalex.org/W1989944203","https://openalex.org/W1998479724","https://openalex.org/W2546839375","https://openalex.org/W2149530645","https://openalex.org/W2061135126","https://openalex.org/W52396946","https://openalex.org/W2184716188","https://openalex.org/W3013368808","https://openalex.org/W3127593639"],"abstract_inverted_index":{"Approximate":[0],"queries":[1],"on":[2,77,137,194,201],"a":[3,69,95,100,127,133,157,182,188],"collection":[4,167],"of":[5,38,43,64,73,98,116,140,164,172,184,190],"strings":[6,44,50,147],"are":[7,41],"important":[8],"in":[9,26,80,122,148],"many":[10],"applications":[11],"such":[12],"as":[13,28,30,46,94],"record":[14],"linkage,":[15],"spell":[16],"checking,":[17],"and":[18,23,113,168],"Web":[19],"search,":[20],"where":[21],"inconsistencies":[22],"errors":[24],"exist":[25],"data":[27,196],"well":[29],"queries.":[31,173,191,227],"Several":[32],"existing":[33],"algorithms":[34,66],"use":[35],"the":[36,49,62,81,107,110,114,138,161,165,170,199,215],"concept":[37],"\"grams,\"":[39],"which":[40],"substrings":[42],"used":[45],"signatures":[47],"for":[48,131,179,187,224],"to":[51,150,220],"build":[52],"index":[53,86,162],"structures.":[54],"A":[55],"recently":[56],"proposed":[57],"technique,":[58],"called":[59],"VGRAM,":[60,99],"improves":[61],"performance":[63,115,171,203],"these":[65,206],"by":[67,144,205],"using":[68,88],"carefully":[70],"chosen":[71],"dictionary":[72,112,159,183],"variable-length":[74],"grams":[75,90,142,186,223],"based":[76],"their":[78],"requencies":[79],"string":[82,166,226],"collection.":[83],"Since":[84],"an":[85,177],"structure":[87,163],"fixed-length":[89],"can":[91],"be":[92],"viewed":[93],"special":[96],"case":[97],"fundamental":[101],"problem":[102,121],"arises":[103],"naturally:":[104],"what":[105],"is":[106,214],"relationship":[108],"between":[109],"gram":[111,158],"queries?":[117],"We":[118,125,154,174],"study":[119,213],"this":[120,123,212],"paper.":[124],"propose":[126,176],"dynamic":[128],"programming":[129],"algorithm":[130,178],"computing":[132,181],"tight":[134],"lower":[135],"bound":[136],"number":[139],"common":[141],"shared":[143],"two":[145],"similar":[146],"order":[149],"improve":[151],"query":[152,202],"performance.":[153],"analyze":[155],"how":[156],"affects":[160],"ultimately":[169],"also":[175],"automatically":[180],"high-quality":[185],"workload":[189],"Our":[192],"experiments":[193],"real":[195],"sets":[197],"show":[198],"improvement":[200],"achieved":[204],"techniques.":[207],"To":[208],"our":[209],"best":[210],"knowledge,":[211],"first":[216],"cost-based":[217],"quantitative":[218],"approach":[219],"deciding":[221],"good":[222],"approximate":[225]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":14},{"year":2012,"cited_by_count":13}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}