An End-to-End OCR Framework for Robust Arabic-Handwriting Recognition using a Novel Transformers-based Model and an Innovative 270 Million-Words Multi-Font Corpus of Classical Arabic with Diacritics (2022 · 3 citations)
Recognizing historical Arabic text is still unreliable. Old printings show inconsistent spelling, cursive and shifted glyphs, ink bleed, stains and decorative layouts with marginal notes, and large labeled datasets are scarce. This second-phase study from Helwan University builds a complete OCR pipeline for Arabic…
GOF at Arabic Hate Speech 2022: Breaking The Loss Function Convention For Data-Imbalanced Arabic Offensive Text Detection (2022 · 2 citations)
The paper addresses offensive-language detection in Arabic tweets for the OSACT5 shared task. The core difficulty is a long-tailed label distribution. In the roughly 13k-tweet dataset of Mubarak et al. (2022), only about 35% of tweets are offensive and 11% are hate speech, and some fine-grained categories are far…
On The Arabic Dialects' Identification: Overcoming Challenges of Geographical Similarities Between Arabic dialects and Imbalanced Datasets (2022 · 2 citations)
The paper describes a system for the NADI 2022 shared task, subtask 1: country-level Arabic dialect identification on tweets.

Co-authors here

3 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 3 times (of the 149,439 papers whose bibliographies we read); 3 citing papers with a page here →.

Updated 1 November 2026