Latent Narratives at AR-MS NakbaNLP 2026: Reducing Character Errors in Arabic Manuscript Transcription: A CER Oriented System
Year: 2026
Type: conference-paper
Abstract: Historic Arabic handwritten texts present significant challenges due to varied handwriting styles, cursive structure, diverse diacritics, and inconsistent character and word sizes.In this work, we introduce Historic-Arabic-OCR, a vision-language OCR system built upon Qari-OCR, which itself is based on Qwen2-VL-2B-Instruct, and further finetuned using Low-Rank Adaptation (LoRA) for Arabic manuscript transcription.The proposed approach incorporates contrast enhancement using CLAHE and deterministic decoding strategies to reduce character-level errors.Our model achieves competitive performance, with a Word Error Rate (WER) of 0.28 and a Character Error Rate (CER) of 0.10 on historical Arabic texts, including low-resolution images.The final submitted system uses CLAHE preprocessing with deterministic greedy decoding to minimize character-level errors.
Author: Sara Abdulmonem Al desouky
Institution: Arab Open University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166510074