{"id":"https://openalex.org/W4386257570","doi":"https://doi.org/10.1109/icit58056.2023.10225830","title":"Correcting Wide-Range of Arabic Spelling Mistakes Using Machine Learning and Transformers","display_name":"Correcting Wide-Range of Arabic Spelling Mistakes Using Machine Learning and Transformers","publication_year":2023,"publication_date":"2023-08-09","ids":{"openalex":"https://openalex.org/W4386257570","doi":"https://doi.org/10.1109/icit58056.2023.10225830"},"language":"en","primary_location":{"id":"doi:10.1109/icit58056.2023.10225830","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icit58056.2023.10225830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Information Technology (ICIT)","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/A5111031700","display_name":"Raghda Diab Hasan","orcid":null},"institutions":[{"id":"https://openalex.org/I114972647","display_name":"University of Jordan","ror":"https://ror.org/05k89ew48","country_code":"JO","type":"education","lineage":["https://openalex.org/I114972647"]}],"countries":["JO"],"is_corresponding":true,"raw_author_name":"Raghda Diab Hasan","raw_affiliation_strings":["The University of Jordan,Computer Engineering Dept,Amman,Jordan","Computer Engineering Dept, The University of Jordan, Amman, Jordan"],"affiliations":[{"raw_affiliation_string":"The University of Jordan,Computer Engineering Dept,Amman,Jordan","institution_ids":["https://openalex.org/I114972647"]},{"raw_affiliation_string":"Computer Engineering Dept, The University of Jordan, Amman, Jordan","institution_ids":["https://openalex.org/I114972647"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036769756","display_name":"Gheith A. Abandah","orcid":"https://orcid.org/0000-0002-0672-809X"},"institutions":[{"id":"https://openalex.org/I114972647","display_name":"University of Jordan","ror":"https://ror.org/05k89ew48","country_code":"JO","type":"education","lineage":["https://openalex.org/I114972647"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Gheith Ali Abandah","raw_affiliation_strings":["The University of Jordan,Computer Engineering Dept,Amman,Jordan","Computer Engineering Dept, The University of Jordan, Amman, Jordan"],"affiliations":[{"raw_affiliation_string":"The University of Jordan,Computer Engineering Dept,Amman,Jordan","institution_ids":["https://openalex.org/I114972647"]},{"raw_affiliation_string":"Computer Engineering Dept, The University of Jordan, Amman, Jordan","institution_ids":["https://openalex.org/I114972647"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5111031700"],"corresponding_institution_ids":["https://openalex.org/I114972647"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1026846,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"405","last_page":"410"},"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/T13629","display_name":"Text Readability and Simplification","score":0.9968000054359436,"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":0.9944999814033508,"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":0.86719810962677},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.8013198375701904},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6907033324241638},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6491929888725281},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6451812386512756},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.526262640953064},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4616391360759735},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.43946802616119385},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.42700210213661194},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1347595751285553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.86719810962677},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.8013198375701904},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6907033324241638},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6491929888725281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6451812386512756},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.526262640953064},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4616391360759735},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.43946802616119385},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.42700210213661194},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1347595751285553},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icit58056.2023.10225830","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icit58056.2023.10225830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Information Technology (ICIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2945743195","https://openalex.org/W3012990076","https://openalex.org/W3034797320","https://openalex.org/W3041181542","https://openalex.org/W3164045210","https://openalex.org/W3186062448","https://openalex.org/W3192770664","https://openalex.org/W3196313137","https://openalex.org/W4200101290","https://openalex.org/W4287182244","https://openalex.org/W4308619130","https://openalex.org/W4308861787","https://openalex.org/W4385245566","https://openalex.org/W4385574130","https://openalex.org/W6739901393","https://openalex.org/W6775150526","https://openalex.org/W6795336613","https://openalex.org/W6846485845","https://openalex.org/W6848910103"],"related_works":["https://openalex.org/W2100947578","https://openalex.org/W2161008081","https://openalex.org/W1555832326","https://openalex.org/W4298186509","https://openalex.org/W2556702969","https://openalex.org/W217221262","https://openalex.org/W611030372","https://openalex.org/W1974418053","https://openalex.org/W2081317458","https://openalex.org/W3037446006"],"abstract_inverted_index":{"Different":[0],"languages":[1],"are":[2],"subject":[3],"to":[4,24,39,48,130],"several":[5],"types":[6],"of":[7,28,42,93,126,171,189,193],"spelling":[8,31,149],"mistakes.":[9,150],"In":[10,117],"this":[11,102,115,143,153],"paper,":[12],"we":[13,88,109,121,139],"use":[14,89,122],"a":[15,76,136,185],"deep":[16],"neural":[17],"network":[18],"machine":[19],"learning":[20],"model":[21,167],"called":[22],"transformer":[23],"correct":[25,169],"wide":[26],"range":[27],"Arabic":[29,94,148,160],"soft":[30],"mistakes":[32],"including:":[33],"lexical":[34],"and":[35,63,67,112,133,191],"semantic":[36],"errors":[37,46,57,71,174],"(due":[38,47],"the":[40,43,49,53,73,118,123,127,172,179,196],"sound":[41],"letter),":[44],"keyboard":[45],"character":[50,186],"position":[51],"on":[52,114,135,195],"keyboard),":[54],"common":[55],"typing":[56,70],"(like":[58],"deleting":[59],"space,":[60],"preposition":[61],"errors,":[62,107],"third":[64],"pronoun":[65],"errors),":[66],"some":[68,79],"random":[69],"when":[72],"user":[74],"replaces":[75],"letter":[77],"with":[78,104],"other":[80],"letter.":[81],"Our":[82],"approach":[83],"has":[84],"two":[85],"stages:":[86],"first,":[87],"huge":[90],"Wiki-40B":[91,180],"dataset":[92,103,137,154],"texts":[95],"which":[96,145,156],"is":[97],"error":[98,187],"free.":[99],"We":[100,151],"inject":[101],"synthetic":[105],"targeted":[106],"then":[108],"perform":[110,131],"training":[111,124,132],"testing":[113,134],"dataset.":[116,181,198],"second":[119],"stage,":[120],"weights":[125],"first":[128],"stage":[129],"that":[138,175],"have":[140],"collected":[141],"for":[142,158],"purpose,":[144],"contains":[146],"real":[147],"call":[152],"REALMS,":[155],"stands":[157],"REal":[159],"Language":[161],"Mistakes":[162],"in":[163],"Spelling.":[164],"The":[165],"proposed":[166],"can":[168],"99.12%":[170],"artificial":[173],"were":[176],"injected":[177],"into":[178],"Additionally,":[182],"it":[183],"achieves":[184],"rate":[188],"1.14%":[190],"accuracy":[192],"98.85%":[194],"REALMS":[197]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}