{"id":"https://openalex.org/W22160234","doi":"https://doi.org/10.19153/cleiej.1.2.3","title":"A Practical q -Gram Index for Text Retrieval Allowing Errors","display_name":"A Practical q -Gram Index for Text Retrieval Allowing Errors","publication_year":2018,"publication_date":"2018-09-25","ids":{"openalex":"https://openalex.org/W22160234","doi":"https://doi.org/10.19153/cleiej.1.2.3","mag":"22160234"},"language":"en","primary_location":{"id":"doi:10.19153/cleiej.1.2.3","doi":"https://doi.org/10.19153/cleiej.1.2.3","is_oa":true,"landing_page_url":"https://doi.org/10.19153/cleiej.1.2.3","pdf_url":"https://www.clei.org/cleiej/index.php/cleiej/article/download/379/60","source":{"id":"https://openalex.org/S164249298","display_name":"CLEI electronic journal","issn_l":"0717-5000","issn":["0717-5000"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","latindex","poland-20","russia-white-list-4"],"host_organization":"https://openalex.org/P4310315484","host_organization_name":"Latin American Center for Computer Studies","host_organization_lineage":["https://openalex.org/P4310315484"],"host_organization_lineage_names":["Latin American Center for Computer Studies"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CLEI Electronic Journal","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.clei.org/cleiej/index.php/cleiej/article/download/379/60","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080743153","display_name":"Gonzalo Navarro","orcid":"https://orcid.org/0000-0002-2286-741X","observed_orcids":["https://orcid.org/0000-0002-2286-741X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gonzalo Navarro","raw_affiliation_strings":["Depto. de Ciencias de la Computaci"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Depto. de Ciencias de la Computaci","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076204770","display_name":"Ricardo A. Baeza-Yates","orcid":"https://orcid.org/0000-0003-3208-9778","observed_orcids":["https://orcid.org/0000-0003-3208-9778"]},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Ricardo Baeza-Yates","raw_affiliation_strings":["Depto. de Ciencias de la Computacion, U. de Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Depto. de Ciencias de la Computacion, U. de Chile","institution_ids":["https://openalex.org/I69737025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7681,"has_fulltext":true,"cited_by_count":64,"citation_normalized_percentile":{"value":0.67342167,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":98},"biblio":{"volume":"1","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":9.999999747378752e-05,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.0,"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/text-retrieval","display_name":"text retrieval","score":0.6959999799728394},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"approximate string matching","score":0.7440000176429749},{"id":"https://openalex.org/keywords/space-optimization","display_name":"space optimization","score":0.4189999997615814},{"id":"https://openalex.org/keywords/natural-language-text","display_name":"natural language text","score":0.6240000128746033},{"id":"https://openalex.org/keywords/query-cost-estimation","display_name":"query cost estimation","score":0.609000027179718}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.8820598125457764},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8452630043029785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7393715381622314},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.6220434904098511},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.6116520166397095},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.5553671717643738},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.540704071521759},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5226402282714844},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.4838941991329193},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4532049000263214},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.41451483964920044},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4112457036972046},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37727469205856323},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33861833810806274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26437026262283325},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.259311318397522},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1920304298400879},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.1865828037261963},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.18466496467590332},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.1235540509223938},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11055505275726318},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.19153/cleiej.1.2.3","doi":"https://doi.org/10.19153/cleiej.1.2.3","is_oa":true,"landing_page_url":"https://doi.org/10.19153/cleiej.1.2.3","pdf_url":"https://www.clei.org/cleiej/index.php/cleiej/article/download/379/60","source":{"id":"https://openalex.org/S164249298","display_name":"CLEI electronic journal","issn_l":"0717-5000","issn":["0717-5000"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","latindex","poland-20","russia-white-list-4"],"host_organization":"https://openalex.org/P4310315484","host_organization_name":"Latin American Center for Computer Studies","host_organization_lineage":["https://openalex.org/P4310315484"],"host_organization_lineage_names":["Latin American Center for Computer Studies"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CLEI Electronic Journal","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.21.2942","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.21.2942","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcc.uchile.cl/~gnavarro/ps/jclei98.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.638.3757","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.638.3757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcc.uchile.cl/~gnavarro/ps/jclei98.pdf","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:dee15db6434c434e9fbdd377beb9b863","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/dee15db6434c434e9fbdd377beb9b863","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"CLEI Electronic Journal, Vol 1, Iss 2 (2018)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.19153/cleiej.1.2.3","doi":"https://doi.org/10.19153/cleiej.1.2.3","is_oa":true,"landing_page_url":"https://doi.org/10.19153/cleiej.1.2.3","pdf_url":"https://www.clei.org/cleiej/index.php/cleiej/article/download/379/60","source":{"id":"https://openalex.org/S164249298","display_name":"CLEI electronic journal","issn_l":"0717-5000","issn":["0717-5000"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","latindex","poland-20","russia-white-list-4"],"host_organization":"https://openalex.org/P4310315484","host_organization_name":"Latin American Center for Computer Studies","host_organization_lineage":["https://openalex.org/P4310315484"],"host_organization_lineage_names":["Latin American Center for Computer Studies"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CLEI Electronic Journal","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W22160234.pdf","grobid_xml":"https://content.openalex.org/works/W22160234.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7099906019","https://openalex.org/W1714821586","https://openalex.org/W7097831774","https://openalex.org/W7099105492","https://openalex.org/W2018599113","https://openalex.org/W3037815103","https://openalex.org/W2017392697","https://openalex.org/W1534635981","https://openalex.org/W2625992059","https://openalex.org/W7100906240"],"abstract_inverted_index":{"We":[0,111,162],"propose":[1],"an":[2,113],"indexing":[3],"technique":[4],"for":[5,17,89,136,183],"approximate":[6],"text":[7,44,62,86,184],"searching,":[8],"which":[9,74,107],"is":[10,28,51,70,129,132,179],"practical":[11,181],"and":[12,14,80,140,152,170],"powerful,":[13],"especially":[15,133],"optimized":[16],"natural":[18,137],"language":[19,138],"text.":[20],"Unlike":[21],"other":[22],"indices":[23],"of":[24,46,101,127,149,156,173,195],"this":[25],"kind,":[26],"it":[27,65,178],"able":[29],"to":[30,59,98,115,142,159,193],"retrieve":[31],"any":[32],"string":[33],"that":[34,123,177],"approximately":[35],"matches":[36],"the":[37,54,61,78,85,117,124,146,150,153,157,160,165,196],"search":[38,68,151],"pattern,":[39],"not":[40],"only":[41],"words.":[42],"Every":[43],"substring":[45],"a":[47,90,180],"fixed":[48],"length":[49],"q":[50],"stored":[52],"in":[53,77,84,144],"index,":[55,79,175],"together":[56],"with":[57],"pointers":[58,97],"all":[60,81],"positions":[63,103],"where":[64],"appears.":[66],"The":[67,186],"pattern":[69,118],"partitioned":[71],"into":[72,120],"pieces":[73,121],"are":[75,87,189],"searched":[76],"their":[82],"occurrences":[83],"verified":[88],"complete":[91],"match.":[92],"To":[93],"reduce":[94],"space":[95,168],"requirements,":[96],"blocks":[99],"instead":[100],"exact":[102],"can":[104],"be":[105],"used,":[106],"increases":[108],"querying":[109,171],"costs.":[110],"design":[112],"algorithm":[114],"optimize":[116],"partition":[119],"so":[122],"total":[125],"number":[126],"verifications":[128],"minimized.":[130],"This":[131],"well":[134],"suited":[135],"texts,":[139],"allows":[141],"know":[143],"advance":[145],"expected":[147,154],"cost":[148],"relevance":[155],"query":[158],"user.":[161],"show":[163],"experimentally":[164],"building":[166],"time,":[167],"requirements":[169],"time":[172],"our":[174],"finding":[176],"alternative":[182],"retrieval.":[185],"retrieval":[187],"times":[188],"reduced":[190],"from":[191],"10%":[192],"60%":[194],"best":[197],"on-line":[198],"algorithm.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}
