{"id":"https://openalex.org/W7125829411","doi":"https://doi.org/10.1109/icit64950.2025.11049091","title":"SAHDA: A Semantic-Aware Hybrid Approach for Arabic Spell Checking with Domain Adaptation","display_name":"SAHDA: A Semantic-Aware Hybrid Approach for Arabic Spell Checking with Domain Adaptation","publication_year":2025,"publication_date":"2025-05-27","ids":{"openalex":"https://openalex.org/W7125829411","doi":"https://doi.org/10.1109/icit64950.2025.11049091"},"language":null,"primary_location":{"id":"doi:10.1109/icit64950.2025.11049091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icit64950.2025.11049091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 12th 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/A5124049836","display_name":"Mossa\u2019B Ibrahim","orcid":null},"institutions":[{"id":"https://openalex.org/I121748325","display_name":"Universidad Complutense de Madrid","ror":"https://ror.org/02p0gd045","country_code":"ES","type":"education","lineage":["https://openalex.org/I121748325"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Mossa\u2019B Ibrahim","raw_affiliation_strings":["Universidad Complutense de Madrid,Facultad de Inform&#x00E1;tica,Madrid,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Complutense de Madrid,Facultad de Inform&#x00E1;tica,Madrid,Spain","institution_ids":["https://openalex.org/I121748325"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034536236","display_name":"Pablo Gerv\u00e1s","orcid":"https://orcid.org/0000-0003-4906-9837"},"institutions":[{"id":"https://openalex.org/I121748325","display_name":"Universidad Complutense de Madrid","ror":"https://ror.org/02p0gd045","country_code":"ES","type":"education","lineage":["https://openalex.org/I121748325"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pablo Gerv\u00e1s","raw_affiliation_strings":["Universidad Complutense de Madrid,Facultad de Inform&#x00E1;tica,Madrid,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Complutense de Madrid,Facultad de Inform&#x00E1;tica,Madrid,Spain","institution_ids":["https://openalex.org/I121748325"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123965599","display_name":"Gonzalo M\u00e9ndez","orcid":null},"institutions":[{"id":"https://openalex.org/I121748325","display_name":"Universidad Complutense de Madrid","ror":"https://ror.org/02p0gd045","country_code":"ES","type":"education","lineage":["https://openalex.org/I121748325"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Gonzalo M\u00e9ndez","raw_affiliation_strings":["Universidad Complutense de Madrid,Facultad de Inform&#x00E1;tica,Madrid,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Complutense de Madrid,Facultad de Inform&#x00E1;tica,Madrid,Spain","institution_ids":["https://openalex.org/I121748325"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5124049836"],"corresponding_institution_ids":["https://openalex.org/I121748325"],"apc_list":null,"apc_paid":null,"fwci":2.0951,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92636142,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"343","last_page":"348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.582099974155426,"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":0.582099974155426,"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":0.08320000022649765,"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/T12090","display_name":"Language and cultural evolution","score":0.05180000141263008,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5182999968528748},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.49300000071525574},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.4372999966144562},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.43639999628067017},{"id":"https://openalex.org/keywords/standardization","display_name":"Standardization","score":0.42250001430511475},{"id":"https://openalex.org/keywords/spell","display_name":"Spell","score":0.42179998755455017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7475000023841858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5293999910354614},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5182999968528748},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.49300000071525574},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.482699990272522},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.4372999966144562},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.43639999628067017},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.42250001430511475},{"id":"https://openalex.org/C2780957641","wikidata":"https://www.wikidata.org/wiki/Q1999796","display_name":"Spell","level":2,"score":0.42179998755455017},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.353300005197525},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.32409998774528503},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icit64950.2025.11049091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icit64950.2025.11049091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 12th International Conference on Information Technology (ICIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7098119854927063}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Arabic":[0],"spell":[1],"checking":[2],"faces":[3],"inherent":[4],"linguistic":[5,58,92],"challenges":[6],"due":[7],"to":[8,37,89,109],"its":[9],"complex":[10],"word":[11],"structures":[12],"and":[13,21,68,77,94,113],"ambiguous":[14,111],"spellings,":[15],"where":[16],"roots":[17],"generate":[18],"diverse":[19,150],"forms":[20],"identical":[22],"spellings":[23],"mask":[24],"multiple":[25],"meanings.":[26],"Current":[27],"systems":[28],"often":[29],"prioritize":[30],"technical":[31],"accuracy":[32],"over":[33],"contextual":[34],"understanding,":[35],"struggling":[36],"preserve":[38],"regional":[39,91,126],"dialects":[40],"or":[41],"resolve":[42,110],"semantic":[43,66],"ambiguities.":[44],"This":[45],"paper":[46],"introduces":[47],"SAHDA,":[48],"a":[49,144],"hybrid":[50],"framework":[51,133],"that":[52,98],"bridges":[53],"computational":[54],"methods":[55],"with":[56,141],"human":[57],"expertise.":[59],"By":[60],"combining":[61],"rule-based":[62],"error":[63],"detection,":[64],"neural":[65],"analysis,":[67],"collaborative":[69],"human-AI":[70],"refinement,":[71],"SAHDA":[72],"addresses":[73],"both":[74],"structural":[75],"errors":[76],"meaning-based":[78],"ambiguities":[79],"in":[80,153],"written":[81,151],"Arabic.":[82],"Key":[83],"innovations":[84],"include":[85],"context-aware":[86],"dialect":[87],"preservation":[88],"maintain":[90],"diversity":[93],"adaptive":[95],"learning":[96],"techniques":[97],"enable":[99],"efficient":[100],"customization":[101],"for":[102,147],"specialized":[103],"domains.":[104],"Evaluations":[105],"demonstrate":[106],"SAHDA\u2019s":[107],"ability":[108],"terms":[112],"dialectal":[114,142],"variations":[115],"more":[116],"effectively":[117],"than":[118],"existing":[119],"approaches":[120],"while":[121],"minimizing":[122],"overcorrection":[123],"of":[124],"valid":[125],"expressions.":[127],"As":[128],"an":[129],"open-source":[130],"tool,":[131],"the":[132,154],"advances":[134],"inclusive":[135],"language":[136],"technology":[137],"by":[138],"harmonizing":[139],"standardization":[140],"richness\u2014":[143],"critical":[145],"advancement":[146],"supporting":[148],"Arabic\u2019s":[149],"traditions":[152],"digital":[155],"age.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-01-28T00:00:00"}
