UzRoberta: A pre-trained language model for Uzbek

Abstract

I would like to introduce the UzLUE standard, which stands for Uzbek Language Understanding Evaluation. A challenge for understanding the natural language of Uzbek (NLU) is UzLUE, which includes message classification. Build jobs from scratch using a diverse source corpus while respecting copyright to make it fully accessible for everyone. We use this UzLUE-RoBERTa, a pre-trained language model (PLM), to support replication of the base model in UzLUE and facilitate future research. We found that UzLUE-RoBERT [1]-base outperforms other baselines including multilingual PLM.

More by Fatima Adilova

• Graph-based density-variation outlier removal for chronic disease prediction: A leakage-free benchmark and component-wise ablationResults in Engineering · 2026
• Monotonic System Framework for Globally Optimal Structuring of Complex Data2026
• Boosting LLM Adaptation: Superior Stability and Convergence via OLoRA+ Across Diverse NLP BenchmarksInternational Siberian workshops and tutorials on electron devices and materials · 2026
• Генерации графов заданной структуры: от глубоких нейронных сетей к квантовым моделям (на примере создания новых лекарств)Problems of Computational and Applied Mathematics · 2026