{"id":"https://openalex.org/W2171972576","doi":"https://doi.org/10.1145/1529282.1529669","title":"Fast error-tolerant search on very large texts","display_name":"Fast error-tolerant search on very large texts","publication_year":2009,"publication_date":"2009-03-08","ids":{"openalex":"https://openalex.org/W2171972576","doi":"https://doi.org/10.1145/1529282.1529669","mag":"2171972576"},"language":"en","primary_location":{"id":"doi:10.1145/1529282.1529669","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1529282.1529669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2009 ACM symposium on Applied Computing","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/A5034440216","display_name":"Marjan Celikik","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Marjan Celikik","raw_affiliation_strings":["Max Planck Institute for Computer Science, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Computer Science, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113677058","display_name":"Holger Bast","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Holger Bast","raw_affiliation_strings":["Max Planck Institute for Computer Science, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Computer Science, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5034440216"],"corresponding_institution_ids":["https://openalex.org/I4210109712"],"apc_list":null,"apc_paid":null,"fwci":2.4997,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89807692,"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":"1724","last_page":"1731"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9988999962806702,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.6377171874046326}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6377171874046326}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1529282.1529669","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1529282.1529669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2009 ACM symposium on Applied Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.434.2464","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.434.2464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://domino.mpi-inf.mpg.de/intranet/ag1/ag1publ.nsf/AuthorEditorIndividualView/efce206882c168ffc125755200522a25/$FILE/spelling-variants.pdf","raw_type":"text"},{"id":"pmh:oai:edoc.mpg.de:518241","is_oa":false,"landing_page_url":"http://edoc.mpg.de/518241","pdf_url":null,"source":{"id":"https://openalex.org/S4406922265","display_name":"Max Planck Institute for Plasma Physics","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":"Shin, Dongwan: The 24th Annual ACM Symposium on Applied Computing, ACM, 1724-1731 (2009)","raw_type":"Conference-Paper"},{"id":"pmh:oai:pure.mpg.de:item_1324112","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-000F-184C-3","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 2009 ACM Symposium On Applied Computing","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1480726700","https://openalex.org/W1489022643","https://openalex.org/W1489753557","https://openalex.org/W1580725209","https://openalex.org/W1976978162","https://openalex.org/W2010595692","https://openalex.org/W2034163998","https://openalex.org/W2038044292","https://openalex.org/W2038218748","https://openalex.org/W2048779798","https://openalex.org/W2057887529","https://openalex.org/W2057900969","https://openalex.org/W2082690166","https://openalex.org/W2085763602","https://openalex.org/W2093537029","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2102443632","https://openalex.org/W2117084652","https://openalex.org/W2121516976","https://openalex.org/W2153987307","https://openalex.org/W2494048233","https://openalex.org/W6671690886","https://openalex.org/W6991161748"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2093578348","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2766271392","https://openalex.org/W2350741829","https://openalex.org/W3004735627"],"abstract_inverted_index":{"We":[0,100,189],"consider":[1],"the":[2,34,41,53,66,81,86,89,94,97,105,166,195],"following":[3,42],"spelling":[4,24,62,115,124],"variants":[5,25,125],"clustering":[6,126],"problem:":[7],"Given":[8],"a":[9,45,119,155,171,180,199],"list\\n":[10],"of":[11,26,36,40,68,88,96,108,173,182],"distinct":[12],"words,":[13],"called":[14],"lexicon,":[15,141],"compute":[16],"(possibly":[17],"overlapping)":[18],"clusters":[19],"of\\n":[20,161],"words":[21,55],"which":[22],"are":[23],"each":[27],"other.":[28],"This":[29,64,164],"problem":[30,127],"naturally":[31],"\\narises\\n":[32],"in":[33,135,150,186,198,208],"context":[35],"error-tolerant":[37,203],"full-text":[38],"search":[39,77,204],"kind:":[43],"For\\n":[44],"given":[46],"query,":[47,90],"return":[48],"not":[49,92],"only":[50],"documents":[51],"matching":[52,60],"query":[54,213],"exactly":[56],"but\\n":[57],"also":[58],"those":[59],"their":[61],"variants.":[63],"is":[65,84,129],"inverse":[67],"the\\n":[69,123],"well-known":[70],"\"Did":[71],"you":[72],"mean:":[73],"...":[74],"?\"":[75],"web":[76],"engine":[78,197],"feature,":[79],"where":[80],"error\\n":[82],"tolerance":[83],"on":[85,93,110,154],"side":[87,95],"and":[91,114,132,137,178],"documents.":[98],"\\n\\n":[99],"combine":[101],"various":[102],"ideas":[103],"from":[104],"large":[106],"body":[107],"literature":[109],"approximate\\n":[111],"string":[112],"searching":[113],"correction":[116],"techniques":[117],"to":[118],"new":[120],"algorithm":[121],"for":[122],"that":[128],"both":[130],"accurate":[131],"very":[133],"efficient\\n":[134],"time":[136,177],"space.":[138,163],"Our":[139],"largest":[140],"containing":[142],"roughly":[143],"10":[144,159],"million":[145],"words,\\n":[146],"can":[147],"be":[148],"processed":[149],"about":[151],"16":[152],"minutes":[153],"standard":[156],"PC":[157],"using":[158],"MB":[160],"additional":[162],"beats":[165],"previously":[167],"best":[168],"scheme":[169],"by":[170,179],"factor":[172,181],"two":[174],"in\\n":[175],"running":[176],"more":[183],"than":[184],"ten":[185],"space":[187],"usage.":[188],"have\\n":[190],"integrated":[191],"our":[192],"algorithms":[193],"into":[194],"CompleteSearch":[196],"way":[200],"that\\n":[201],"achieves":[202],"without":[205],"significant":[206],"blowup":[207],"neither":[209],"index":[210],"\\nsize\\n":[211],"nor":[212],"processing":[214],"time.":[215]},"counts_by_year":[{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}