ARTIFICIAL INTELLIGENCE APPROACHES TO THE ANALYSIS OF AVIATION TERMINOLOGY IN UZBEK AND ENGLISH LANGUAGES
Abstract
The rapid development of aviation necessitates precise terminology management across multilingual contexts, particularly between widely used English aviation terms and emerging Uzbek equivalents. This paper explores artificial intelligence approaches, including natural language processing (NLP), machine learning classification, and semantic analysis techniques, for comparative analysis of aviation terminology in Uzbek and English. Key methods such as transformer-based embeddings, cross-lingual word alignment, and terminology extraction models are examined to identify semantic equivalences, context-specific variations, and translation challenges. Findings demonstrate that multilingual BERT models achieve high accuracy in terminology mapping, supporting standardized aviation communication in Uzbekistan's growing aerospace sector. The study provides a framework for AI-driven terminology databases to enhance safety and interoperability.