QORAQALPOQ VA O‘ZBEK TILLARINING SINTAKTIK MODELLARINI TEGLASH MASALASI
Keywords:
Tagging, syntactic unit, word combinations, Universal Dependencies (UD)Abstract
This article explores the Universal Dependencies (UD) system and its application in the Uzbek and Karakalpak languages. It analyzes the tagging process and its significance in Natural Language Processing (NLP), especially in stages such as tokenization, lemmatization, and stemming. The paper describes how UD is used to define parts of speech, morphological, and syntactic features, particularly in the annotation of word combinations in Uzbek.
References
1. Ch, Taguchi. Consistent Grammatical Annotation of Turkic Languages for more Universal Dependencies.
2. Abduraxmonova N. Mashina tarjimasining lingvistik asoslari. – T., 2012.
3. Mengliev, D., Barakhnin, V., & Abdurakhmonova, N. (2021). Development of intellectual web system for morph analyzing of uzbek words. Applied Sciences, 11(19), 9117.
4. Abdurakhmonova, N. (2019). Dependency parsing based on Uzbek Corpus. In of the International Conference on Language Technologies for All (LT4All).
5. Alkım.E, Çebi. Y. Machine Translation Infrastructure for Turkic Languages (MT-Turk).–Turkiya-2019.
6. Benita Pungwe Mpala. THE USE OF ADVANCED TECHNOLOGY TO FIND SOLUTIONS FOR HUMANITARIAN ISSUES.–San Fransisko, 2020. P–20.
7. Brown,P.F., Cocke, J., Della Pietra, S.A., Mercer, R. L. The Mathematics of Statistical Machine Translation:Parameter Estimation. Computational linguistics, 19(2),–P.263-311.
