{"id":"https://openalex.org/W2011971739","doi":"https://doi.org/10.1145/2457465.2457470","title":"Efficient fuzzy search in large text collections","display_name":"Efficient fuzzy search in large text collections","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2011971739","doi":"https://doi.org/10.1145/2457465.2457470","mag":"2011971739"},"language":"en","primary_location":{"id":"doi:10.1145/2457465.2457470","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2457465.2457470","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-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/A5036444203","display_name":"Hannah Bast","orcid":"https://orcid.org/0000-0003-1213-6776"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Hannah Bast","raw_affiliation_strings":["Albert Ludwigs University, Freiburg, Germany"],"affiliations":[{"raw_affiliation_string":"Albert Ludwigs University, Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034440216","display_name":"Marjan Celikik","orcid":null},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marjan Celikik","raw_affiliation_strings":["Albert Ludwigs University, Freiburg, Germany"],"affiliations":[{"raw_affiliation_string":"Albert Ludwigs University, Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5036444203"],"corresponding_institution_ids":["https://openalex.org/I161046081"],"apc_list":null,"apc_paid":null,"fwci":1.596,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.83079536,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"31","issue":"2","first_page":"1","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998999834060669,"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":0.9998999834060669,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9993000030517578,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8643954992294312},{"id":"https://openalex.org/keywords/full-text-search","display_name":"Full text search","score":0.7554858922958374},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7150063514709473},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.6453423500061035},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.49682000279426575},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4809390902519226},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.41302740573883057},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33397865295410156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2787494659423828},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.253978431224823},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.18405580520629883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8643954992294312},{"id":"https://openalex.org/C20228898","wikidata":"https://www.wikidata.org/wiki/Q83540","display_name":"Full text search","level":3,"score":0.7554858922958374},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7150063514709473},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.6453423500061035},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.49682000279426575},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4809390902519226},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.41302740573883057},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33397865295410156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2787494659423828},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.253978431224823},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18405580520629883}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2457465.2457470","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2457465.2457470","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W1484435918","https://openalex.org/W1489753557","https://openalex.org/W1534635981","https://openalex.org/W1545097943","https://openalex.org/W1556741196","https://openalex.org/W1564094940","https://openalex.org/W1570051269","https://openalex.org/W1580725209","https://openalex.org/W1593185626","https://openalex.org/W1647671624","https://openalex.org/W1834151548","https://openalex.org/W1887000090","https://openalex.org/W1902405276","https://openalex.org/W1977618577","https://openalex.org/W2001496424","https://openalex.org/W2010027198","https://openalex.org/W2011373486","https://openalex.org/W2011632873","https://openalex.org/W2018838261","https://openalex.org/W2030756600","https://openalex.org/W2037679238","https://openalex.org/W2038044292","https://openalex.org/W2038807029","https://openalex.org/W2040102554","https://openalex.org/W2044966609","https://openalex.org/W2045821558","https://openalex.org/W2053550438","https://openalex.org/W2054899689","https://openalex.org/W2055247965","https://openalex.org/W2057887529","https://openalex.org/W2057900969","https://openalex.org/W2060108852","https://openalex.org/W2065259291","https://openalex.org/W2066102695","https://openalex.org/W2074231493","https://openalex.org/W2078993594","https://openalex.org/W2079473728","https://openalex.org/W2085218027","https://openalex.org/W2093537029","https://openalex.org/W2096932043","https://openalex.org/W2097184821","https://openalex.org/W2097284241","https://openalex.org/W2097571242","https://openalex.org/W2097776316","https://openalex.org/W2098326081","https://openalex.org/W2100751585","https://openalex.org/W2103014446","https://openalex.org/W2109056561","https://openalex.org/W2111299261","https://openalex.org/W2117084652","https://openalex.org/W2121516976","https://openalex.org/W2121806125","https://openalex.org/W2124814993","https://openalex.org/W2129271949","https://openalex.org/W2133137130","https://openalex.org/W2140795521","https://openalex.org/W2145674808","https://openalex.org/W2150916025","https://openalex.org/W2153190022","https://openalex.org/W2158779275","https://openalex.org/W2161936973","https://openalex.org/W2162592052","https://openalex.org/W2165156013","https://openalex.org/W2167847032","https://openalex.org/W2170521549","https://openalex.org/W2171743956","https://openalex.org/W2171972576","https://openalex.org/W2172230252","https://openalex.org/W2582397176","https://openalex.org/W4389615663","https://openalex.org/W6629116644"],"related_works":["https://openalex.org/W118734887","https://openalex.org/W2352030744","https://openalex.org/W2111281114","https://openalex.org/W2349570474","https://openalex.org/W4282568653","https://openalex.org/W1514026108","https://openalex.org/W2011971739","https://openalex.org/W2359796251","https://openalex.org/W176895657","https://openalex.org/W2008508464"],"abstract_inverted_index":{"We":[0,71,94],"consider":[1,95],"the":[2,23,26,32,35,101,108,120,130,161],"problem":[3],"of":[4,25,34,69,87],"fuzzy":[5,58],"full-text":[6,14,45,59],"search":[7,15,46,60],"in":[8,107,129],"large":[9,82],"text":[10,64,83],"collections,":[11],"that":[12,76],"is,":[13],"which":[16],"is":[17,138],"robust":[18],"against":[19],"errors":[20],"both":[21],"on":[22,31,62,81],"side":[24,33],"query":[27,52,79,102,121],"as":[28,30,151],"well":[29,42],"documents.":[36],"Standard":[37],"inverted-index":[38],"techniques":[39,75],"work":[40],"extremely":[41],"for":[43,57],"ordinary":[44],"but":[47],"fail":[48],"to":[49,143],"achieve":[50,77],"interactive":[51,78],"times":[53,80],"(below":[54],"100":[55],"milliseconds)":[56],"even":[61],"moderately-sized":[63],"collections":[65,84],"(above":[66],"10":[67],"GBs":[68],"text).":[70],"present":[72],"new":[73],"preprocessing":[74],"(100":[85],"GB":[86],"text,":[88],"served":[89],"by":[90],"a":[91,126],"single":[92],"machine).":[93],"two":[96],"similarity":[97],"measures,":[98],"one":[99,118],"where":[100,119],"terms":[103,106,122,124],"match":[104,123],"similar":[105,127],"collection":[109,131],"(e.g.,":[110,132],"algorithm":[111],"matches":[112,134],"algoritm":[113],"or":[114],"vice":[115],"versa)":[116],"and":[117],"with":[125],"prefix":[128],"alori":[133],"algorithm).":[135],"The":[136],"latter":[137],"important":[139],"when":[140],"we":[141],"want":[142],"display":[144],"results":[145],"instantly":[146],"after":[147],"each":[148],"keystroke":[149],"(search":[150],"you":[152],"type).":[153],"All":[154],"algorithms":[155],"have":[156],"been":[157],"fully":[158],"integrated":[159],"into":[160],"CompleteSearch":[162],"engine.":[163]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}