{"id":"https://openalex.org/W2117084652","doi":"https://doi.org/10.1162/0891201042544938","title":"Fast Approximate Search in Large Dictionaries","display_name":"Fast Approximate Search in Large Dictionaries","publication_year":2004,"publication_date":"2004-11-25","ids":{"openalex":"https://openalex.org/W2117084652","doi":"https://doi.org/10.1162/0891201042544938","mag":"2117084652"},"language":"en","primary_location":{"id":"doi:10.1162/0891201042544938","is_oa":true,"landing_page_url":"https://doi.org/10.1162/0891201042544938","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/0891201042544938","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/0891201042544938","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114255303","display_name":"Stoyan Mihov","orcid":null},"institutions":[{"id":"https://openalex.org/I24768866","display_name":"Bulgarian Academy of Sciences","ror":"https://ror.org/01x8hew03","country_code":"BG","type":"government","lineage":["https://openalex.org/I24768866"]},{"id":"https://openalex.org/I4210134980","display_name":"Institute for Parallel Processing","ror":"https://ror.org/047hhy227","country_code":"BG","type":"facility","lineage":["https://openalex.org/I24768866","https://openalex.org/I4210134980"]}],"countries":["BG"],"is_corresponding":false,"raw_author_name":"Stoyan Mihov","raw_affiliation_strings":["Bulgarian Academy of Sciences, Linguistic Modelling Department, Institute for Parallel Processing, Bulgarian Academy of Sciences, 25A, Akad. G. Bonchev Str., 1113 Sofia, Bulgaria","Bulgarian Academy of Sciences, Linguistic Modelling Department, Institute for Parallel Processing, Bulgarian Academy of Sciences, 25A, Akad. G. Bonchev Str., 1113 Sofia, Bulgaria. E-mail:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bulgarian Academy of Sciences, Linguistic Modelling Department, Institute for Parallel Processing, Bulgarian Academy of Sciences, 25A, Akad. G. Bonchev Str., 1113 Sofia, Bulgaria","institution_ids":["https://openalex.org/I24768866","https://openalex.org/I4210134980"]},{"raw_affiliation_string":"Bulgarian Academy of Sciences, Linguistic Modelling Department, Institute for Parallel Processing, Bulgarian Academy of Sciences, 25A, Akad. G. Bonchev Str., 1113 Sofia, Bulgaria. E-mail:","institution_ids":["https://openalex.org/I24768866","https://openalex.org/I4210134980"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109699155","display_name":"Klaus U. Schulz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210088543","display_name":"Institut f\u00fcr Informationsverarbeitung","ror":"https://ror.org/0047j9t38","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210088543"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klaus U. Schulz","raw_affiliation_strings":["University of Munich, Centrum f\u00fcr Informations-und Sprachverarbeitung, Ludwig-Maximilians-Universit\u00e4t-M\u00fcnchen, Oettingenstr. 67, 80538 Munchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Munich, Centrum f\u00fcr Informations-und Sprachverarbeitung, Ludwig-Maximilians-Universit\u00e4t-M\u00fcnchen, Oettingenstr. 67, 80538 Munchen, Germany","institution_ids":["https://openalex.org/I4210088543","https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.5105,"has_fulltext":true,"cited_by_count":67,"citation_normalized_percentile":{"value":0.96301234,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"30","issue":"4","first_page":"451","last_page":"477"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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/T11567","display_name":"semigroups and automata theory","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/levenshtein-distance","display_name":"Levenshtein distance","score":0.8121137619018555},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7853394746780396},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6693376302719116},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.5727906823158264},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5630509257316589},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4844803512096405},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45784276723861694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41399484872817993},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19912999868392944}],"concepts":[{"id":"https://openalex.org/C2777515626","wikidata":"https://www.wikidata.org/wiki/Q496939","display_name":"Levenshtein distance","level":2,"score":0.8121137619018555},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7853394746780396},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6693376302719116},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.5727906823158264},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5630509257316589},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4844803512096405},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45784276723861694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41399484872817993},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19912999868392944},{"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1162/0891201042544938","is_oa":true,"landing_page_url":"https://doi.org/10.1162/0891201042544938","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/0891201042544938","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.58.4626","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.58.4626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.uni-muenchen.de/people/Schulz/Pub/fastapproxsearch.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.67.6424","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.67.6424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://lml.bas.bg/~stoyan/J04-4003.pdf","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:7a714e3b07e64abfb3f68b2cfa5d0a18","is_oa":false,"landing_page_url":"https://doaj.org/article/7a714e3b07e64abfb3f68b2cfa5d0a18","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,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 30, Iss 4 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/0891201042544938","is_oa":true,"landing_page_url":"https://doi.org/10.1162/0891201042544938","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/0891201042544938","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320882","display_name":"Volkswagen Foundation","ror":"https://ror.org/03bsmfz84"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2117084652.pdf","grobid_xml":"https://content.openalex.org/works/W2117084652.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W27881537","https://openalex.org/W82777215","https://openalex.org/W1487429615","https://openalex.org/W1515839227","https://openalex.org/W1521776429","https://openalex.org/W1529615245","https://openalex.org/W1548701969","https://openalex.org/W1563342424","https://openalex.org/W1647671624","https://openalex.org/W1650656906","https://openalex.org/W1902405276","https://openalex.org/W1969698078","https://openalex.org/W1970026646","https://openalex.org/W1997204547","https://openalex.org/W1999378673","https://openalex.org/W2001496424","https://openalex.org/W2002089154","https://openalex.org/W2010595692","https://openalex.org/W2011632873","https://openalex.org/W2012659300","https://openalex.org/W2016219933","https://openalex.org/W2019363722","https://openalex.org/W2020035298","https://openalex.org/W2020103094","https://openalex.org/W2023358833","https://openalex.org/W2023843553","https://openalex.org/W2040102554","https://openalex.org/W2041486018","https://openalex.org/W2042850423","https://openalex.org/W2043481183","https://openalex.org/W2045821558","https://openalex.org/W2055247965","https://openalex.org/W2055846397","https://openalex.org/W2057887529","https://openalex.org/W2062235741","https://openalex.org/W2065546971","https://openalex.org/W2066102695","https://openalex.org/W2074064717","https://openalex.org/W2093537029","https://openalex.org/W2099510384","https://openalex.org/W2105491669","https://openalex.org/W2110314280","https://openalex.org/W2154478838","https://openalex.org/W2165156013","https://openalex.org/W2168459716","https://openalex.org/W2950053197","https://openalex.org/W4214671568","https://openalex.org/W4231741839"],"related_works":["https://openalex.org/W2461708070","https://openalex.org/W2003932770","https://openalex.org/W1531307672","https://openalex.org/W4362583275","https://openalex.org/W2575897682","https://openalex.org/W2844405045","https://openalex.org/W4285090010","https://openalex.org/W4280559639","https://openalex.org/W4321609555","https://openalex.org/W2788104449"],"abstract_inverted_index":{"The":[0,116],"need":[1],"to":[2,50,107,129],"correct":[3],"garbled":[4],"strings":[5],"arises":[6],"in":[7,42,112],"many":[8],"areas":[9],"of":[10,28,39,85,100,137,155,167,176],"natural":[11,26],"language":[12],"processing.":[13],"If":[14],"a":[15,25,54,74,77,86,113],"dictionary":[16,44],"is":[17,36],"available":[18],"that":[19,144],"covers":[20],"all":[21,40],"possible":[22],"input":[23,34,138,162,178],"tokens,":[24],"set":[27,38],"candidates":[29],"for":[30,45,65,134,147,160],"correcting":[31],"an":[32,168],"erroneous":[33],"P":[35],"the":[37,43,47,83,98,109,152,165,174,177],"words":[41],"which":[46,119,158],"Levenshtein":[48,88],"distance":[49],"Pdoes":[51],"not":[52],"exceed":[53],"given":[55],"(small)":[56],"bound":[57],"k.":[58],"In":[59],"this":[60],"article":[61],"we":[62,90],"describe":[63],"methods":[64,95],"efficiently":[66],"selecting":[67],"such":[68],"candidate":[69],"sets.":[70],"After":[71],"introducing":[72],"as":[73],"starting":[75],"point":[76],"basic":[78,110],"correction":[79,132,145,156],"method":[80,171],"based":[81],"on":[82,151,173],"concept":[84],"\u201cuniversal":[87],"automaton,\u201d":[89],"show":[91],"how":[92],"two":[93],"filtering":[94,170],"known":[96],"from":[97],"field":[99],"approximate":[101],"text":[102],"search":[103],"can":[104],"be":[105],"used":[106],"improve":[108],"procedure":[111],"significant":[114],"way.":[115],"first":[117],"method,":[118],"uses":[120],"standard":[121],"dictionaries":[122,124],"plus":[123],"with":[125],"reversed":[126],"words,":[127],"leads":[128],"very":[130],"short":[131],"times":[133,146],"most":[135],"classes":[136],"strings.":[139],"Our":[140],"evaluation":[141],"results":[142],"demonstrate":[143],"fixed-distance":[148],"bounds":[149],"depend":[150],"expected":[153],"number":[154],"candidates,":[157],"decreases":[159],"longer":[161],"words.":[163,179],"Similarly":[164],"choice":[166],"optimal":[169],"depends":[172],"length":[175]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
