{"id":"https://openalex.org/W7160242521","doi":"https://doi.org/10.63317/4o6byujewowg","title":"English Language Spelling Correction as an Information Retrieval Task Using Wikipedia Search Statistics","display_name":"English Language Spelling Correction as an Information Retrieval Task Using Wikipedia Search Statistics","publication_year":2022,"publication_date":"2022-06-01","ids":{"openalex":"https://openalex.org/W7160242521","doi":"https://doi.org/10.63317/4o6byujewowg"},"language":"en","primary_location":{"id":"doi:10.63317/4o6byujewowg","doi":"https://doi.org/10.63317/4o6byujewowg","is_oa":true,"landing_page_url":"https://doi.org/10.63317/4o6byujewowg","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.48.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","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":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.48.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056370767","display_name":"Kyle Goslin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210144925","display_name":"Technological University Dublin","ror":"https://ror.org/04t0qbt32","country_code":"IE","type":"education","lineage":["https://openalex.org/I4210144925"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Kyle Goslin","raw_affiliation_strings":["TU Dublin -Blanchardstown Campus Blanchardstown Road North , Dublin 15 , Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Dublin -Blanchardstown Campus Blanchardstown Road North , Dublin 15 , Ireland","institution_ids":["https://openalex.org/I4210144925"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135396983","display_name":"Markus Hofmann","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210144925","display_name":"Technological University Dublin","ror":"https://ror.org/04t0qbt32","country_code":"IE","type":"education","lineage":["https://openalex.org/I4210144925"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Markus Hofmann","raw_affiliation_strings":["TU Dublin -Blanchardstown Campus Blanchardstown Road North , Dublin 15 , Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Dublin -Blanchardstown Campus Blanchardstown Road North , Dublin 15 , Ireland","institution_ids":["https://openalex.org/I4210144925"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210144925"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27992476,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"458","last_page":"464"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9976000189781189,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9976000189781189,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.0007999999797903001,"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/T11269","display_name":"Algorithms and Data Compression","score":0.0005000000237487257,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spelling-correction","display_name":"spelling correction","score":0.9700000286102295},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"information retrieval","score":0.7319999933242798},{"id":"https://openalex.org/keywords/acronyms","display_name":"acronyms","score":0.6809999942779541},{"id":"https://openalex.org/keywords/morphological-variation","display_name":"morphological variation","score":0.7590000033378601}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922000288963318},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.7056000232696533},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6424999833106995},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6270999908447266},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5993000268936157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5652999877929688},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.47189998626708984},{"id":"https://openalex.org/C2987496018","wikidata":"https://www.wikidata.org/wiki/Q1860","display_name":"English language","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C21025794","wikidata":"https://www.wikidata.org/wiki/Q5141219","display_name":"Cognitive models of information retrieval","level":4,"score":0.32109999656677246},{"id":"https://openalex.org/C2778842860","wikidata":"https://www.wikidata.org/wiki/Q986551","display_name":"Cross-language information retrieval","level":3,"score":0.31380000710487366},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.29679998755455017},{"id":"https://openalex.org/C90288658","wikidata":"https://www.wikidata.org/wiki/Q3318149","display_name":"Human\u2013computer information retrieval","level":3,"score":0.2903999984264374},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28679999709129333},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26669999957084656},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C116425068","wikidata":"https://www.wikidata.org/wiki/Q4686695","display_name":"Adversarial information retrieval","level":5,"score":0.25200000405311584},{"id":"https://openalex.org/C182861755","wikidata":"https://www.wikidata.org/wiki/Q5158391","display_name":"Concept search","level":4,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.63317/4o6byujewowg","doi":"https://doi.org/10.63317/4o6byujewowg","is_oa":true,"landing_page_url":"https://doi.org/10.63317/4o6byujewowg","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.48.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","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":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.63317/4o6byujewowg","doi":"https://doi.org/10.63317/4o6byujewowg","is_oa":true,"landing_page_url":"https://doi.org/10.63317/4o6byujewowg","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.48.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","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":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.6450560092926025,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7160242521.pdf","grobid_xml":"https://content.openalex.org/works/W7160242521.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2089316759","https://openalex.org/W20984399","https://openalex.org/W7096478877","https://openalex.org/W1502332103","https://openalex.org/W7096613993","https://openalex.org/W66690650","https://openalex.org/W2087824626","https://openalex.org/W1993301141","https://openalex.org/W1494632860","https://openalex.org/W2140608987"],"abstract_inverted_index":{"Spelling":[0],"correction":[1,13,55,121,141,160,175,191,201],"utilities":[2,14],"have":[3],"become":[4],"commonplace":[5],"during":[6],"the":[7,18,48,60,67,90,116,125,129,138,153,157,188],"writing":[8],"process,":[9],"however,":[10],"many":[11],"spelling":[12,40,54,120,159,174,190,200],"suffer":[15],"due":[16],"to":[17,25,72,85,197],"size":[19],"and":[20,30,43,77,106,143,147,150],"quality":[21],"of":[22,33,50,70,80,111,118,137,152,165,183],"dictionaries":[23],"available":[24],"aid":[26,73],"correction.Many":[27],"terms,":[28,89],"acronyms,":[29],"morphological":[31],"variations":[32],"terms":[34],"are":[35],"often":[36],"missing,":[37],"leaving":[38],"potential":[39],"errors":[41],"unidentified":[42],"potentially":[44],"uncorrected.This":[45],"research":[46,113,167,185],"describes":[47],"implementation":[49,117],"WikiSpell,":[51,193],"a":[52,81,96,119,135,169],"dynamic":[53,171],"tool":[56],"that":[57,123,177,187],"relies":[58],"on":[59],"Wikipedia":[61,130],"dataset":[62,131],"search":[63,107,132],"API":[64],"functionality":[65],"as":[66,95],"sole":[68],"source":[69],"knowledge":[71],"misspelled":[74],"term":[75],"identification":[76],"automatic":[78],"replacement.Instead":[79],"traditional":[82],"matching":[83,105],"process":[84,92,101],"select":[86],"candidate":[87],"replacement":[88,91],"is":[93,168],"treated":[94],"natural":[97],"language":[98],"information":[99,172],"retrieval":[100],"harnessing":[102],"wildcard":[103,126],"string":[104],"result":[108],"statistics.The":[109],"aims":[110],"this":[112,166,184],"include:":[114],"1)":[115],"algorithm":[122,155,176],"utilizes":[124],"operators":[127],"in":[128],"API,":[133],"2)":[134],"review":[136],"current":[139],"spell":[140],"tools":[142],"approaches":[144],"being":[145],"utilized,":[146],"3)":[148],"testing":[149],"validation":[151],"developed":[154],"against":[156],"benchmark":[158],"tool,":[161],"Hunspell.The":[162],"key":[163],"contribution":[164],"robust,":[170],"retrieval-based":[173],"does":[178],"not":[179],"require":[180],"prior":[181],"training.Results":[182],"show":[186],"proposed":[189],"algorithm,":[192,202],"achieved":[194],"comparable":[195],"results":[196],"an":[198],"industry-standard":[199],"Hunspell.":[203]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-05-06T00:00:00"}
