{"id":"https://openalex.org/W2166655588","doi":"https://doi.org/10.5539/cis.v5n3p37","title":"Context-sensitive Spelling Correction Using Google Web 1T 5-Gram Information","display_name":"Context-sensitive Spelling Correction Using Google Web 1T 5-Gram Information","publication_year":2012,"publication_date":"2012-04-25","ids":{"openalex":"https://openalex.org/W2166655588","doi":"https://doi.org/10.5539/cis.v5n3p37","mag":"2166655588"},"language":"en","primary_location":{"id":"doi:10.5539/cis.v5n3p37","is_oa":true,"landing_page_url":"https://doi.org/10.5539/cis.v5n3p37","pdf_url":"https://ccsenet.org/journal/index.php/cis/article/download/14173/11078","source":{"id":"https://openalex.org/S2764452479","display_name":"Computer and Information Science","issn_l":"1913-8989","issn":["1913-8989","1913-8997"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322531","host_organization_name":"Canadian Center of Science and Education","host_organization_lineage":["https://openalex.org/P4310322531"],"host_organization_lineage_names":["Canadian Center of Science and Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer and Information Science","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ccsenet.org/journal/index.php/cis/article/download/14173/11078","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Youssef Bassil","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Youssef Bassil","raw_affiliation_strings":["LACSC -Lebanese Association for Computational Sciences, Beirut, Lebanon"],"affiliations":[{"raw_affiliation_string":"LACSC -Lebanese Association for Computational Sciences, Beirut, Lebanon","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Mohammad Alwani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammad Alwani","raw_affiliation_strings":["LACSC -Lebanese Association for Computational Sciences, Beirut, Lebanon"],"affiliations":[{"raw_affiliation_string":"LACSC -Lebanese Association for Computational Sciences, Beirut, Lebanon","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3377,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.84838475,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"5","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8115000128746033,"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":0.8115000128746033,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.021400000900030136,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.019600000232458115,"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/spelling","display_name":"Spelling","score":0.8176000118255615},{"id":"https://openalex.org/keywords/spell","display_name":"Spell","score":0.7074000239372253},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7031000256538391},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.6018999814987183},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5644999742507935},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5318999886512756},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4756999909877777},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4717999994754791}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9021000266075134},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.8176000118255615},{"id":"https://openalex.org/C2780957641","wikidata":"https://www.wikidata.org/wiki/Q1999796","display_name":"Spell","level":2,"score":0.7074000239372253},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7031000256538391},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.6018999814987183},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5644999742507935},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5318999886512756},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5174000263214111},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.503600001335144},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4756999909877777},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4717999994754791},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45509999990463257},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C170748874","wikidata":"https://www.wikidata.org/wiki/Q21117977","display_name":"Proofreading","level":4,"score":0.2637999951839447},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5539/cis.v5n3p37","is_oa":true,"landing_page_url":"https://doi.org/10.5539/cis.v5n3p37","pdf_url":"https://ccsenet.org/journal/index.php/cis/article/download/14173/11078","source":{"id":"https://openalex.org/S2764452479","display_name":"Computer and Information Science","issn_l":"1913-8989","issn":["1913-8989","1913-8997"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322531","host_organization_name":"Canadian Center of Science and Education","host_organization_lineage":["https://openalex.org/P4310322531"],"host_organization_lineage_names":["Canadian Center of Science and Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer and Information Science","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1204.5852","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1204.5852","pdf_url":"https://arxiv.org/pdf/1204.5852","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.5539/cis.v5n3p37","is_oa":true,"landing_page_url":"https://doi.org/10.5539/cis.v5n3p37","pdf_url":"https://ccsenet.org/journal/index.php/cis/article/download/14173/11078","source":{"id":"https://openalex.org/S2764452479","display_name":"Computer and Information Science","issn_l":"1913-8989","issn":["1913-8989","1913-8997"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322531","host_organization_name":"Canadian Center of Science and Education","host_organization_lineage":["https://openalex.org/P4310322531"],"host_organization_lineage_names":["Canadian Center of Science and Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer and Information Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2166655588.pdf","grobid_xml":"https://content.openalex.org/works/W2166655588.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W140368687","https://openalex.org/W142212369","https://openalex.org/W1550267443","https://openalex.org/W1562624811","https://openalex.org/W1647671624","https://openalex.org/W1970026646","https://openalex.org/W1972099155","https://openalex.org/W1993301141","https://openalex.org/W1994790623","https://openalex.org/W1995426156","https://openalex.org/W2010595692","https://openalex.org/W2014516359","https://openalex.org/W2016871293","https://openalex.org/W2042657851","https://openalex.org/W2055496638","https://openalex.org/W2059800182","https://openalex.org/W2066792529","https://openalex.org/W2109469864","https://openalex.org/W2114342377","https://openalex.org/W2116625254","https://openalex.org/W2118975565","https://openalex.org/W2118996379","https://openalex.org/W2124479173","https://openalex.org/W2127836646","https://openalex.org/W2157963512","https://openalex.org/W6602210249","https://openalex.org/W6645048466","https://openalex.org/W6648982606","https://openalex.org/W6811685372"],"related_works":[],"abstract_inverted_index":{"In":[0,220],"computing,":[1],"spell":[2,23,37,54],"checking":[3],"is":[4,25,46,227],"the":[5,41,44,47,103,151,156,224,235,239],"process":[6],"of":[7,33,73,141,145,194,214,238],"detecting":[8,115],"and":[9,84,95,116,119,180,200,210,217,242],"sometimes":[10],"providing":[11],"spelling":[12,111,206],"suggestions":[13],"for":[14,114],"incorrectly":[15],"spelled":[16],"words":[17,34,74],"in":[18,102,122],"a":[19,22,26,31,87,108,142,166,172,192,211,221],"text.":[20,104],"Basically,":[21],"checker":[24],"computer":[27],"program":[28],"that":[29,53,163,176,184],"uses":[30],"dictionary":[32,42],"to":[35,98,228,233],"perform":[36],"checking.":[38],"The":[39,51,126],"bigger":[40],"is,":[43],"higher":[45],"error":[48,92,161,182,187,207,240],"detection":[49,93,241],"rate.":[50],"fact":[52],"checkers":[55],"are":[56],"based":[57,170],"on":[58,171,191],"regular":[59],"dictionaries,":[60],"they":[61,68,89],"suffer":[62],"from":[63,132,150,197],"data":[64,130,137],"sparseness":[65],"problem":[66],"as":[67,232],"cannot":[69],"capture":[70],"large":[71],"vocabulary":[72],"including":[75],"proper":[76],"names,":[77],"domain-specific":[78],"terms,":[79],"technical":[80],"jargons,":[81],"special":[82],"acronyms,":[83],"terminologies.":[85],"As":[86],"result,":[88],"exhibit":[90],"low":[91],"rate":[94,209],"often":[96],"fail":[97],"catch":[99],"major":[100],"errors":[101,121],"This":[105],"paper":[106],"proposes":[107],"new":[109],"context-sensitive":[110],"correction":[112,178,208,243],"method":[113,158],"correcting":[117],"non-word":[118,216],"real-word":[120,218],"digital":[123],"text":[124,195],"documents.":[125],"approach":[127],"hinges":[128],"around":[129],"statistics":[131],"Google":[133],"Web":[134],"1T":[135],"5-gram":[136],"set":[138,193],"which":[139],"consists":[140],"big":[143],"volume":[144],"n-gram":[146],"word":[147],"sequences,":[148],"extracted":[149],"World":[152],"Wide":[153],"Web.":[154],"Fundamentally,":[155],"proposed":[157,225],"comprises":[159],"an":[160,181,204],"detector":[162],"detects":[164],"misspellings,":[165,202],"candidate":[167],"spellings":[168],"generator":[169],"character":[173],"2-gram":[174],"model":[175],"generates":[177],"suggestions,":[179],"corrector":[183],"performs":[185],"contextual":[186],"correction.":[188],"Experiments":[189],"conducted":[190],"documents":[196],"different":[198],"domains":[199],"containing":[201],"showed":[203],"outstanding":[205],"drastic":[212],"reduction":[213],"both":[215],"errors.":[219],"further":[222],"study,":[223],"algorithm":[226],"be":[229],"parallelized":[230],"so":[231],"lower":[234],"computational":[236],"cost":[237],"processes.":[244]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2016-06-24T00:00:00"}
