{"id":"https://openalex.org/W2945743195","doi":"https://doi.org/10.1109/taslp.2019.2918404","title":"Real-Word Errors in Arabic Texts: A Better Algorithm for Detection and Correction","display_name":"Real-Word Errors in Arabic Texts: A Better Algorithm for Detection and Correction","publication_year":2019,"publication_date":"2019-05-22","ids":{"openalex":"https://openalex.org/W2945743195","doi":"https://doi.org/10.1109/taslp.2019.2918404","mag":"2945743195"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2918404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2918404","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","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/A5059302775","display_name":"Aqil M. Azmi","orcid":"https://orcid.org/0000-0002-0983-2861"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Aqil M. Azmi","raw_affiliation_strings":["Department of Computer Science, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-0983-2861","affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073592896","display_name":"Manal N. Almutery","orcid":null},"institutions":[{"id":"https://openalex.org/I1284598098","display_name":"King Abdulaziz City for Science and Technology","ror":"https://ror.org/05tdz6m39","country_code":"SA","type":"facility","lineage":["https://openalex.org/I1284598098"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Manal N. Almutery","raw_affiliation_strings":["National Center for Computer Technology and Applied Mathematics, King Abdulaziz City for Science and Technology, Riyadh, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Center for Computer Technology and Applied Mathematics, King Abdulaziz City for Science and Technology, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I1284598098"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027010923","display_name":"Hatim Aboalsamh","orcid":"https://orcid.org/0000-0002-8000-5105"},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Hatim A. Aboalsamh","raw_affiliation_strings":["Department of Computer Science, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":2.2293,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.90322219,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"27","issue":"8","first_page":"1308","last_page":"1320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9962000250816345,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7970332503318787},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7697882652282715},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.6185426115989685},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5832911729812622},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5576949715614319},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.5557128190994263},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.5396679639816284},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5379889607429504},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5339670777320862},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5129558444023132},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5093656778335571},{"id":"https://openalex.org/keywords/mistake","display_name":"Mistake","score":0.4793965816497803},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4165620803833008},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3544258773326874},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.29398590326309204},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13955512642860413},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13276338577270508}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7970332503318787},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7697882652282715},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.6185426115989685},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5832911729812622},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5576949715614319},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.5557128190994263},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.5396679639816284},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5379889607429504},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5339670777320862},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5129558444023132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5093656778335571},{"id":"https://openalex.org/C2777179996","wikidata":"https://www.wikidata.org/wiki/Q911222","display_name":"Mistake","level":2,"score":0.4793965816497803},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4165620803833008},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3544258773326874},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29398590326309204},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13955512642860413},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13276338577270508},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2019.2918404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2918404","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W173352366","https://openalex.org/W937194849","https://openalex.org/W1507727839","https://openalex.org/W1540550673","https://openalex.org/W1554944419","https://openalex.org/W1565050238","https://openalex.org/W1586934900","https://openalex.org/W1604792744","https://openalex.org/W1627539022","https://openalex.org/W1647671624","https://openalex.org/W1680392829","https://openalex.org/W1984708705","https://openalex.org/W1984972187","https://openalex.org/W1993301141","https://openalex.org/W1996824467","https://openalex.org/W2002938383","https://openalex.org/W2004744189","https://openalex.org/W2010595692","https://openalex.org/W2012191724","https://openalex.org/W2016871293","https://openalex.org/W2040102554","https://openalex.org/W2047744234","https://openalex.org/W2050584996","https://openalex.org/W2066792529","https://openalex.org/W2097927681","https://openalex.org/W2103333826","https://openalex.org/W2109469864","https://openalex.org/W2118996379","https://openalex.org/W2133990480","https://openalex.org/W2139212933","https://openalex.org/W2147272182","https://openalex.org/W2148362501","https://openalex.org/W2157800108","https://openalex.org/W2158195707","https://openalex.org/W2171033594","https://openalex.org/W2201502411","https://openalex.org/W2250816155","https://openalex.org/W2251291091","https://openalex.org/W2287447024","https://openalex.org/W2294192051","https://openalex.org/W2330587814","https://openalex.org/W2333629957","https://openalex.org/W2343984634","https://openalex.org/W2394855683","https://openalex.org/W2583662888","https://openalex.org/W2741814453","https://openalex.org/W2911374865","https://openalex.org/W2949916273","https://openalex.org/W2964322605","https://openalex.org/W3193477162","https://openalex.org/W4211260480","https://openalex.org/W6624471508","https://openalex.org/W6635057008","https://openalex.org/W6636875271","https://openalex.org/W6636915900","https://openalex.org/W6637386731","https://openalex.org/W6675969814","https://openalex.org/W6683333045","https://openalex.org/W6691525129","https://openalex.org/W6696199271","https://openalex.org/W6697035680","https://openalex.org/W6703022592","https://openalex.org/W6890250144"],"related_works":["https://openalex.org/W1590719878","https://openalex.org/W4244271513","https://openalex.org/W4376622330","https://openalex.org/W2365974527","https://openalex.org/W4306382224","https://openalex.org/W2159992105","https://openalex.org/W2130596402","https://openalex.org/W2124470186","https://openalex.org/W168676510","https://openalex.org/W3105992103"],"abstract_inverted_index":{"Real-word":[0,62],"(also":[1],"known":[2],"as":[3,68],"semantic":[4],"or":[5],"context-sensitive)":[6],"spelling":[7],"error":[8,13,28,190],"is":[9,40,178,192],"a":[10,31,34,45,80,126,152],"class":[11],"of":[12,27,48,111,129,156,174,188,206],"that":[14,83,113],"escapes":[15],"the":[16,73,90,109,133,163,186,196],"typical":[17],"spell":[18,81],"checker":[19,82],"which":[20,169],"relies":[21],"on":[22],"dictionary":[23],"look-up.":[24],"This":[25,194],"kind":[26],"occurs":[29],"when":[30,185],"user":[32],"types":[33],"correctly":[35],"spelled":[36],"word-by":[37],"mistake-when":[38],"another":[39],"intended,":[41],"e.g.,":[42],"\u201cI":[43],"want":[44],"peace":[46],"(piece)":[47],"cake.\u201d":[49],"Further,":[50],"these":[51],"errors":[52,63,88,201],"commonly":[53],"arise":[54],"in":[55,171,202],"text":[56],"written":[57],"by":[58,102],"people":[59],"with":[60,148,180],"dyslexia.":[61],"are":[64],"harder":[65],"to":[66,71],"detect":[67,123],"we":[69,78,136,166],"need":[70],"consider":[72],"context.":[74],"In":[75],"this":[76,106],"paper,":[77],"propose":[79],"detects":[84],"and":[85,117,124,139,154,158],"corrects":[86],"real-word":[87,130,189],"for":[89,162,199],"Arabic":[91,207],"language.":[92],"Our":[93,176],"method":[94],"avoids":[95],"predefined":[96],"confusion":[97],"sets-a":[98],"simple":[99],"approach":[100],"used":[101],"many":[103],"works":[104],"tackling":[105],"problem-which":[107],"limits":[108],"list":[110],"words":[112,191],"can":[114,122],"be":[115],"detected":[116],"corrected.":[118],"Thus,":[119],"our":[120],"system":[121,197],"correct":[125],"larger":[127],"set":[128],"errors.":[131],"For":[132],"detection":[134],"phase,":[135],"employ":[137],"word":[138],"stem":[140],"n-gram":[141],"(n":[142],"=":[143],"1-3)":[144],"language":[145],"model":[146],"along":[147],"machine":[149],"learning,":[150],"achieving":[151],"precision":[153],"recall":[155],"83.5%":[157],"99.2%,":[159],"respectively.":[160],"And":[161],"correction":[164],"phase":[165],"use":[167],"n-gram,":[168],"results":[170],"an":[172,181],"accuracy":[173],"98%.":[175],"scheme":[177],"robust,":[179],"excellent":[182],"performance":[183],"even":[184],"percentage":[187],"high.":[193],"makes":[195],"suitable":[198],"handling":[200],"post":[203],"OCR":[204],"recognition":[205],"text.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}