OTLARNING SEMANTIK TASNIFIDA XALQARO STANDART TEGLASH TIZIMLARIDAN FOYDALANISHNING NAZARIY ASOSLARI
Keywords:
semantic field, semantic hierarchy, tag, lexicology, noun, WordNet, USAS, FrameNet, SRL, ISO 24617-8, semantic classification, corpus linguistics, machine translation, ontological resourcesAbstract
This article examines the issue of classifying and tagging lexical units of the noun category in the Uzbek language into semantic fields. The study explores the theoretical and practical aspects of grouping words by meaning and placing them into hierarchical structures. The experience of international semantic tagging systems such as WordNet, FrameNet, USAS, PropBank, PDT, Vallex, Crovallex, and the Ukrainian Semantic Lexicon is analyzed. Over 1,000 noun samples in the Uzbek language are categorized into 14 main semantic fields and their subcategories based on ISO 24617-8 standards and WordNet classifications, and assigned corresponding tags. The research highlights the differences between the concepts of semantic fields and hierarchies, as well as their interrelation, presented in a comparative manner. The results demonstrate that the tagging system achieved a 92% accuracy rate, confirming its effectiveness for the Uzbek language. The practical significance of semantic tagging in areas such as machine translation, text analysis, and information retrieval is discussed. In conclusion, recommendations are provided for creating semantic corpora and dictionaries for the Uzbek language, outlining directions for future research. This work contributes to a deeper understanding of the lexical richness of the Uzbek language in the context of digital technologies and strengthens its position in international linguistic studies.
References
Gries S. Th., Berez A. L. Linguistic annotation in/for corpus linguistics // Ide N., Pustejovsky J. (eds.). Handbook of Linguistic Annotation. – Dordrecht: Springer, 2017.
Sharipova M. E. Semantic Field of the Word // International Conference on Developments in Education, Sciences and Humanities. – Washington (USA), 2022. – 20–21 mart. – S. 163–168.
Abduraxmonova N. Z., Xaydarov M. R. O‘zbek tilida WordNet yaratish masalalariga doir // O‘zbekistonda xorijiy tillar: ilmiy-metodik elektron jurnal. – 2019. – №4 (27). – B. 19–27.
Unit 4: Corpus annotation // Educational material on corpus linguistics. – B.e.k. (bosma er va kuni ko‘rsatilmagan).
Gantar P., Štrkalj Despot K., Krek S., Ljubešić N. Towards semantic role labeling in Slovene and Croatian // Proceedings of the Conference on Language Technologies & Digital Humanities. – Ljubljana, 2018.
