{"id":"https://openalex.org/W4415422015","doi":"https://doi.org/10.15439/2025f4862","title":"AraXLM: Evaluating Arabic Diacritization Tools for Cross-Language Plagiarism Detection","display_name":"AraXLM: Evaluating Arabic Diacritization Tools for Cross-Language Plagiarism Detection","publication_year":2025,"publication_date":"2025-10-15","ids":{"openalex":"https://openalex.org/W4415422015","doi":"https://doi.org/10.15439/2025f4862"},"language":"en","primary_location":{"id":"doi:10.15439/2025f4862","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2025f4862","pdf_url":"https://annals-csis.org/Volume_43/drp/pdf/4862.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://annals-csis.org/Volume_43/drp/pdf/4862.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Mona Alshehri","orcid":"https://orcid.org/0000-0002-4193-6230"},"institutions":[{"id":"https://openalex.org/I162608824","display_name":"University of Sussex","ror":"https://ror.org/00ayhx656","country_code":"GB","type":"education","lineage":["https://openalex.org/I162608824"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mona Alshehri","raw_affiliation_strings":["Dept. of Informatics, University of Sussex"],"raw_orcid":"https://orcid.org/0000-0002-4193-6230","affiliations":[{"raw_affiliation_string":"Dept. of Informatics, University of Sussex","institution_ids":["https://openalex.org/I162608824"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028279177","display_name":"Natalia Beloff","orcid":"https://orcid.org/0000-0002-8872-7786"},"institutions":[{"id":"https://openalex.org/I162608824","display_name":"University of Sussex","ror":"https://ror.org/00ayhx656","country_code":"GB","type":"education","lineage":["https://openalex.org/I162608824"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Natalia Beloff","raw_affiliation_strings":["Dept. of Informatics, University of Sussex"],"raw_orcid":"https://orcid.org/0000-0002-8872-7786","affiliations":[{"raw_affiliation_string":"Dept. of Informatics, University of Sussex","institution_ids":["https://openalex.org/I162608824"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052669359","display_name":"Martin White","orcid":"https://orcid.org/0000-0001-8686-2274"},"institutions":[{"id":"https://openalex.org/I162608824","display_name":"University of Sussex","ror":"https://ror.org/00ayhx656","country_code":"GB","type":"education","lineage":["https://openalex.org/I162608824"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Martin White","raw_affiliation_strings":["Dept. of Informatics, University of Sussex"],"raw_orcid":"https://orcid.org/0000-0001-8686-2274","affiliations":[{"raw_affiliation_string":"Dept. of Informatics, University of Sussex","institution_ids":["https://openalex.org/I162608824"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162608824"],"apc_list":null,"apc_paid":null,"fwci":1.3736,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83317763,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":"43","issue":null,"first_page":"451","last_page":"460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.9950000047683716,"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/T13629","display_name":"Text Readability and Simplification","score":0.9950000047683716,"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/T11492","display_name":"Academic integrity and plagiarism","score":0.9835000038146973,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9810000061988831,"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/plagiarism-detection","display_name":"Plagiarism detection","score":0.39629998803138733},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.34610000252723694},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.32179999351501465},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.27790001034736633},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.23829999566078186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6406000256538391},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5393000245094299},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5045999884605408},{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.39629998803138733},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32829999923706055},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.23829999566078186},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.23010000586509705}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.15439/2025f4862","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2025f4862","pdf_url":"https://annals-csis.org/Volume_43/drp/pdf/4862.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:doaj.org/article:6579caaa9ea44f65bd39cec147d78215","is_oa":true,"landing_page_url":"https://doaj.org/article/6579caaa9ea44f65bd39cec147d78215","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Annals of computer science and information systems, Vol 43, Pp 451-460 (2025)","raw_type":"article"},{"id":"pmh:oai:figshare.com:article/29586236","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/AraXLM_evaluating_Arabic_diacritization_tools_for_cross-_language_plagiarism_detection/29586236","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"}],"best_oa_location":{"id":"doi:10.15439/2025f4862","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2025f4862","pdf_url":"https://annals-csis.org/Volume_43/drp/pdf/4862.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415422015.pdf","grobid_xml":"https://content.openalex.org/works/W4415422015.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2009784977","https://openalex.org/W2107878631","https://openalex.org/W2115416945","https://openalex.org/W2250751111","https://openalex.org/W2471147443","https://openalex.org/W2472854096","https://openalex.org/W2580962661","https://openalex.org/W2739351760","https://openalex.org/W2739702159","https://openalex.org/W2740272870","https://openalex.org/W2753924560","https://openalex.org/W2795864747","https://openalex.org/W2946627182","https://openalex.org/W2971724044","https://openalex.org/W2984342083","https://openalex.org/W3092557781","https://openalex.org/W3102201419","https://openalex.org/W3104033643","https://openalex.org/W3166011548","https://openalex.org/W3213351479","https://openalex.org/W4200304220","https://openalex.org/W4385192620","https://openalex.org/W4390280155","https://openalex.org/W4399593357","https://openalex.org/W4402671409","https://openalex.org/W4404872520","https://openalex.org/W4407767146","https://openalex.org/W6960297043"],"related_works":[],"abstract_inverted_index":{"In":[0,189],"recent":[1],"years,":[2],"plagiarism":[3,95,247],"detection":[4,96,245],"systems":[5],"have":[6,32],"evolved":[7],"from":[8],"basic":[9],"lexical":[10],"matching":[11],"and":[12,62,144,149,166,182,193,220,227],"n-gram":[13],"overlap":[14],"methods":[15],"to":[16,46,68],"Deep":[17],"Learning":[18],"(DL)":[19],"models":[20,67,132,210],"capable":[21],"of":[22,53,66,83,93,111,120,230,246],"capturing":[23],"semantic":[24,60,231,253],"relationships":[25],"between":[26,255],"texts.":[27,77],"While":[28],"these":[29],"DL-based":[30],"approaches":[31],"achieved":[33],"notable":[34],"success":[35],"across":[36,200],"various":[37],"languages,":[38],"their":[39],"effectiveness":[40],"in":[41,75,173],"Arabic":[42,76,84,212,249],"remains":[43],"limited":[44],"due":[45],"inherent":[47],"linguistic":[48],"ambiguities,":[49],"particularly":[50],"the":[51,64,90,108,112,118,179,228,234],"omission":[52],"diacritical":[54],"marks.":[55],"This":[56,78],"absence":[57],"hinders":[58],"accurate":[59,208],"interpretation":[61],"limits":[63],"ability":[65],"detect":[69],"paraphrased":[70],"or":[71],"semantically":[72],"obfuscated":[73],"content":[74],"paper":[79],"presents":[80],"an":[81],"evaluation":[82],"Text":[85],"Diacritization":[86],"(ATD)":[87],"tools":[88,159],"as":[89,161,216],"initial":[91],"phase":[92],"a":[94],"framework":[97],"designed":[98],"for":[99],"Arabic\u2013English":[100],"cross-lingual":[101],"model":[102],"text":[103,225],"analysis":[104,126],"(AraXLM).":[105],"It":[106],"describes":[107],"first":[109],"stage":[110],"framework,":[113,236],"which":[114],"focuses":[115],"on":[116,129],"assessing":[117],"performance":[119],"state-of-the-art":[121],"ATD":[122,131],"tools.":[123],"An":[124],"empirical":[125],"was":[127],"conducted":[128],"six":[130],"using":[133],"Word":[134],"Error":[135,139],"Rate":[136,140],"(WER),":[137],"Diacritic":[138],"(DER),":[141],"both":[142,201],"with":[143],"without":[145],"case":[146],"endings":[147],"(CE),":[148],"Bilingual":[150],"Evaluation":[151],"Understudy":[152],"(BLEU)":[153],"metrics.":[154,202],"The":[155],"results":[156],"show":[157],"that":[158,206],"such":[160,215],"Shakkelha":[162],"produced":[163],"lower":[164],"DER":[165],"high":[167,171],"BLEU":[168],"values,":[169],"indicating":[170],"accuracy":[172],"diacritic":[174],"restoration,":[175],"while":[176],"Fine-Tashkeel":[177],"demonstrates":[178],"lowest":[180],"WER":[181],"highest":[183],"BLEU,":[184],"reflecting":[185],"best":[186],"word-level":[187],"performance.":[188],"contrast,":[190],"CAMeL":[191],"Tools":[192],"Mishkal":[194],"display":[195],"comparatively":[196],"higher":[197],"error":[198],"rates":[199],"These":[203],"findings":[204],"suggest":[205],"incorporating":[207],"diacritization":[209,240],"into":[211],"NLP":[213],"tasks,":[214],"Machine":[217],"Translation":[218],"(MT)":[219],"Plagiarism":[221],"Detection":[222],"(PD),":[223],"improves":[224],"normalisation":[226],"quality":[229],"embeddings.":[232],"Thus,":[233],"AraXLM":[235],"supported":[237],"by":[238],"effective":[239],"pre-processing,":[241],"enhances":[242],"linguistically":[243],"aware":[244],"involving":[248],"text,":[250],"where":[251],"precise":[252],"alignment":[254],"languages":[256],"is":[257],"essential.":[258]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-09-02T18:50:13.731487","created_date":"2025-10-24T00:00:00"}
