Developing A Question-Answering System In The Uzbek Language Based On The Xlm-Roberta Model

Abstract

This article presents the issue of testing the XML-RoBERTa model for generating questions and answers in the Uzbek language. In the study, the XML-RoBERTa model was adapted to the Uzbek language from a dataset consisting of context, question and answer pairs in the Uzbek language and, as a result, a model was developed to generate a fragment of the answer to the user's question from the context. ROUGE, EM (Exact Match) and F1 control metrics were used to determine the performance of the model.

More by Ilyos Khujayorov

• PadSink-Track: A Calibrated Framework for Padding-Sink-Preserving, Alignment-Tracked Selective Cross-Attention Key–Value Cache Access in CPU-Based Whisper Speech RecognitionTechnologies · 2026
• A Cache-Aware Compression Framework: Deriving the Compression Target and Stopping Rule for Transformers on CPU-Class HardwareAI · 2026
• Development of Uzbek Question-Answering Models through Fine-Tuning ApproachesInternational Conference on Future Networks and Distributed Systems · 2025 · Citations: 1
• An Ensemble of Convolutional Neural Networks for Sound Event DetectionMathematics · 2025 · Citations: 10