Northwestern 2 at BAREC Shared Task 2026: CAMeLBERT-Mix for Fine-Grained Arabic Readability Assessment
Abstract
AbstractThis paper presents the Northwestern University in Qatar (NU-Q) submission to Task 1 of the BAREC Shared Task 2026 on fine-grained Arabic readability assessment. The task requires predicting the readability level of Arabic sentences across 19 ordered readability levels. Our system fine-tunes CAMeLBERT-Mix as a 19-class classifier using the official BAREC training data and cross-entropy optimization. We evaluate the proposed system using Quadratic Weighted Kappa (QWK), the official shared-task evaluation metric, together with classification accuracy. Our submitted system achieves a validation QWK of 0.7393 and an accuracy of 45.96%, indicating that pretrained Arabic language models provide a strong baseline for fine-grained Arabic readability assessment.