Giant Cervicothoracic Madelung Disease Presenting with Airway Compromise: A Case Report from Ethiopia
Article scientifique
Open Access
Amanuel Mesfin Oljira, Obsa Biratu Negasa, Diriba Gebeyehu Wakesa
INTRODUCTION: To describe a rare (airway-threatening) cervicothoracic presentation of Madelung disease (multiple symmetric lipomatosis) with upper mediastinal extension and to introduce a reproducible peri-operative strategy …
Correction to: Missing the Window: Barriers to Building Back Better in the Western Cape, South Africa
Article scientifique
Open Access
Robyn Pharoah
'Correction to: Missing the Window: Barriers to Building Back Better in the Western Cape, South Africa' published in 'Natural Hazards and Public Management'
Full Fine-Tuning vs. Parameter-Efficient Adaptation for Low-Resource African ASR: A Controlled Study with Whisper-Small
Article scientifique
Open Access
Sukairaj Hafiz Imam, Muhammad Yahuza Bello, Hadiza Ali Umar
Sukairaj Hafiz Imam, Muhammad Yahuza Bello, Hadiza Ali Umar, Tadesse Destaw Belay, Idris Abdulmumin, Seid Muhie Yimam, Shamsuddeen Hassan Muhammad. Proceedings of the 7th Workshop …
QAMAR: A New Fully Verified and Accurate Quranic Arabic Morphological Analysis Resource.
Article scientifique
Open Access
Sara Faqihi, Karim Bouzoubaa, Rachida Tajmout
Several Quranic morphological corpora have been developed to support Arabic linguistic analysis and NLP applications, yet they often lack full coverage, consistency, or manual verification.We …
REGLAT at AbjadMed: Handling Imbalanced Arabic Medical Text Classification via Hierarchical KNN-MLP Architecture
Article scientifique
Open Access
Ahmed Megahed Fetouh, Mohammed Rahmath, Omer Salih Dawood
In this paper, we demonstrate the system submitted to the shared task of medical text classification in Arabic.We proposed a single-model approach based on finetuned …
NileUn at AbjadGenEval Shared Task: Contrastive Learning with Stacking Ensemble for Efficient Arabic AI-Generated Text Detection
Article scientifique
Open Access
Mohamed Hussein Mohamed, Shrouk Shalaby, Nesreen Mohamed
We present a computationally efficient approach for detecting AI-generated Arabic text as part of the AbjadGenEval shared task.Our method combines Supervised Contrastive Learning with a …
Are investigative centres independent?
Article scientifique
Open Access
Muyanga Innocent Ziba
Investigative journalism has brought both advantages and challenges for journalism in Malawi. As a developing country, Malawi has benefited immensely from this type of journalism. …
Kashif-AI at AbjadGenEval Shared Task: A Transformer-based Approach for Arabic AI-Generated Text Detection
Article scientifique
Open Access
Fatimah Mohamed Emad Eldin
As Large Language Models (LLMs) become increasingly proficient at generating human-like text, distinguishing between human-written and machine-generated content has become a critical challenge for information …
Developing an English–Efik Corpus and Machine Translation System for Digitization Inclusion
Article scientifique
Open Access
Offiong Bassey Edet, Mbuotidem Sunday Awak, Emmanuel Oyo-Ita
Low-resource languages serve as invaluable repositories of human history, preserving cultural and intellectual diversity.Despite their significance, they remain largely absent from modern natural language processing …
MBZUAI at AMIYA Shared Task 2026: Adapting Open-Source LLMs for Dialectal Arabic
Article scientifique
Open Access
Rana Gaber, Yara Allam, Serag Amin
This paper presents our contribution to the closed data track of the AMIYA Shared Task on Dialectal Arabic text generation.In this track, we train fully …
Morphologically-informed Somali Lemmatization Corpus built with a Web-based Crowdsourcing Platform
Article scientifique
Open Access
Abdifatah Ahmed Gedi, Shafie Abdi Mohamed, Yusuf Ahmed Yusuf
Abdifatah Ahmed Gedi, Shafie Abdi Mohamed, Yusuf A. Yusuf, Muhidin A. Mohamed, Fuad Mire Hassan, Houssein A Assowe. Proceedings of the 7th Workshop on African …
What Might Influence Economic Forecasts for the Congo Basin?
Article scientifique
Open Access
Ernest L. Molua, Francis Ebai Ndip, Perez L. Kemeni Kambiet
Abstract While the Congo Basin remains an important repository for biodiversity, the economies of the basin rely on primary commodity exploitation and trade. Renewable and …
Evaluating Retrieval-Augmented Generation for Medication Question Answering on Nigerian Drug Labels in Yorùbá
Article scientifique
Open Access
Zainab Tairu, Aramide Adebesin
Large Language Models (LLMs) have the potential to improve healthcare information access in Nigeria, but they risk generating unsafe or inaccurate responses when used in …
ÒWE-Voice: An Evaluation of Monolingual and Multilingual ASR Model Using Yoruba Proverb Speech Dataset
Article scientifique
Open Access
Daud Olamide Abolade
Given the advancement of various Artificial Intelligence (AI) technologies in the 21st century, Automatic Speech Recognition (ASR) plays a vital role in human and machine …
Alkhalil Corpus: An Open-Source Thematic and Lemmatized Corpus for Modern Standard Arabic
Article scientifique
Open Access
Samir Belayachi, Azzeddine Mazroui
The availability of large annotated corpora remains a major challenge for the development of natural language processing systems for underresourced languages such as Arabic.In this …
An assessment of development and non-development information in selected nigerian newspapers
Article scientifique
Open Access
Alex Eloho Umuerri
The study investigated the incidences of development information in two Nigerian national newspapers, namely, Guardian and Vanguard which were purposively selected to underscore their role …
REGLAT at AbjadGenEval: Multi-Model Ensemble Approach for Arabic AI-Generated Text Detection
Article scientifique
Open Access
Mariam Labib Francies, Nsrin Ashraf, Ahmed Megahed Fetouh
The rapid advancement of large language models necessitates robust methods for detecting AI-generated Arabic text.This paper presents our system for distinguishing human-written from machine-generated Arabic …
Short-form verbal arts as a speech data resource in the field
Article scientifique
Open Access
Matthew Faytak, Tianle Yang, Pius W. Akumbu
We propose a method for efficient field data collection of speech resource data which leverages short-form verbal arts, namely riddles and proverbs, which permit a …
Tashkees-AI at AbjadMed 2026: Flat vs. Hierarchical Classification for Fine-Grained Arabic Medical QA
Article scientifique
Open Access
Fatimah Mohamed Emad Eldin
This paper describes Tashkees-AI, a system developed for the AbjadMed 2026 Shared Task on Arabic Medical Question Classification.A comprehensive empirical study was conducted across 82 …
ART: Attention-Regularized Transformers for Multi-Modal Robustness
Article scientifique
Open Access
Mohammed Bouri, Mohammed Erradi, Adnane Saoud
Transformers have become the standard in Natural Language Processing (NLP) and Computer Vision (CV) due to their strong performance, yet they remain highly sensitive to …