{"id":"https://openalex.org/W7166510074","doi":"https://doi.org/10.63317/3gkghprpz2sb","title":"Latent Narratives at AR-MS NakbaNLP 2026: Reducing Character Errors in Arabic Manuscript Transcription: A CER Oriented System","display_name":"Latent Narratives at AR-MS NakbaNLP 2026: Reducing Character Errors in Arabic Manuscript Transcription: A CER Oriented System","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7166510074","doi":"https://doi.org/10.63317/3gkghprpz2sb"},"language":"en","primary_location":{"id":"doi:10.63317/3gkghprpz2sb","doi":"https://doi.org/10.63317/3gkghprpz2sb","is_oa":true,"landing_page_url":"https://doi.org/10.63317/3gkghprpz2sb","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nakbanlp/pdf/2026.nakbanlp-1.43.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nakbanlp/pdf/2026.nakbanlp-1.43.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139601567","display_name":"Sara Abdulmonem Al desouky","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210139873","display_name":"Arab Open University","ror":"https://ror.org/03vfnky71","country_code":"SA","type":"education","lineage":["https://openalex.org/I4210093932","https://openalex.org/I4210139873"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Sara Abdulmonem Al desouky","raw_affiliation_strings":["Computer Science Department , Arab Open University , KSA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department , Arab Open University , KSA","institution_ids":["https://openalex.org/I4210139873"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5139601567"],"corresponding_institution_ids":["https://openalex.org/I4210139873"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.46582749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"275","last_page":"279"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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"}},{"id":"https://openalex.org/T12707","display_name":"Vehicle License Plate Recognition","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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/optical-character-recognition","display_name":"optical character recognition","score":0.8040000200271606},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.8640000224113464},{"id":"https://openalex.org/keywords/qwen2-vl","display_name":"Qwen2-VL","score":0.7120000123977661},{"id":"https://openalex.org/keywords/low-rank-adaptation","display_name":"low-rank adaptation","score":0.8830000162124634},{"id":"https://openalex.org/keywords/clahe-contrast-enhancement","display_name":"CLAHE contrast enhancement","score":0.871999979019165},{"id":"https://openalex.org/keywords/deterministic-decoding","display_name":"deterministic decoding","score":0.75},{"id":"https://openalex.org/keywords/handwriting-recognition","display_name":"handwriting recognition","score":0.4300000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7684999704360962},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6349999904632568},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5982000231742859},{"id":"https://openalex.org/C2778943297","wikidata":"https://www.wikidata.org/wiki/Q1079418","display_name":"Cursive","level":2,"score":0.5896000266075134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5527999997138977},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5503000020980835},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5117999911308289},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.499099999666214},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.47440001368522644},{"id":"https://openalex.org/C80797182","wikidata":"https://www.wikidata.org/wiki/Q17451","display_name":"Typeface","level":2,"score":0.4458000063896179},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.39959999918937683},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39340001344680786},{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C32717103","wikidata":"https://www.wikidata.org/wiki/Q184759","display_name":"Character encoding","level":3,"score":0.33079999685287476},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.3188000023365021},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C2779386606","wikidata":"https://www.wikidata.org/wiki/Q2393642","display_name":"Handwriting","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C177454536","wikidata":"https://www.wikidata.org/wiki/Q578290","display_name":"Emphasis (telecommunications)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C112640561","wikidata":"https://www.wikidata.org/wiki/Q2440634","display_name":"Handwriting recognition","level":3,"score":0.2924000024795532},{"id":"https://openalex.org/C78148190","wikidata":"https://www.wikidata.org/wiki/Q8192","display_name":"Writing system","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.2799000144004822},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C30387639","wikidata":"https://www.wikidata.org/wiki/Q4680744","display_name":"Adaptive histogram equalization","level":5,"score":0.2587999999523163},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.63317/3gkghprpz2sb","doi":"https://doi.org/10.63317/3gkghprpz2sb","is_oa":true,"landing_page_url":"https://doi.org/10.63317/3gkghprpz2sb","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nakbanlp/pdf/2026.nakbanlp-1.43.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.63317/3gkghprpz2sb","doi":"https://doi.org/10.63317/3gkghprpz2sb","is_oa":true,"landing_page_url":"https://doi.org/10.63317/3gkghprpz2sb","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nakbanlp/pdf/2026.nakbanlp-1.43.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166510074.pdf","grobid_xml":"https://content.openalex.org/works/W7166510074.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7166525157","https://openalex.org/W7166575220","https://openalex.org/W4402671279","https://openalex.org/W7166529330","https://openalex.org/W3172417134","https://openalex.org/W4415131752","https://openalex.org/W7166519090","https://openalex.org/W7166582008","https://openalex.org/W4403882523","https://openalex.org/W7161809699"],"abstract_inverted_index":{"Historic":[0],"Arabic":[1,48,88],"handwritten":[2],"texts":[3],"present":[4],"significant":[5],"challenges":[6],"due":[7],"to":[8,62,103],"varied":[9],"handwriting":[10],"styles,":[11],"cursive":[12],"structure,":[13],"diverse":[14],"diacritics,":[15],"and":[16,19,40,58,78],"inconsistent":[17],"character":[18],"word":[20],"sizes.In":[21],"this":[22],"work,":[23],"we":[24],"introduce":[25],"Historic-Arabic-OCR,":[26],"a":[27,71,79],"vision-language":[28],"OCR":[29],"system":[30,95],"built":[31],"upon":[32],"Qari-OCR,":[33],"which":[34],"itself":[35],"is":[36],"based":[37],"on":[38,86],"Qwen2-VL-2B-Instruct,":[39],"further":[41],"finetuned":[42],"using":[43,56],"Low-Rank":[44],"Adaptation":[45],"(LoRA)":[46],"for":[47],"manuscript":[49],"transcription.The":[50],"proposed":[51],"approach":[52],"incorporates":[53],"contrast":[54],"enhancement":[55],"CLAHE":[57,97],"deterministic":[59,100],"decoding":[60,102],"strategies":[61],"reduce":[63],"character-level":[64,105],"errors.Our":[65],"model":[66],"achieves":[67],"competitive":[68],"performance,":[69],"with":[70,99],"Word":[72],"Error":[73,81],"Rate":[74,82],"(WER)":[75],"of":[76,84],"0.28":[77],"Character":[80],"(CER)":[83],"0.10":[85],"historical":[87],"texts,":[89],"including":[90],"low-resolution":[91],"images.The":[92],"final":[93],"submitted":[94],"uses":[96],"preprocessing":[98],"greedy":[101],"minimize":[104],"errors.":[106]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-06-30T00:00:00"}