The Uzbek language is morphologically rich with numerous affixes, and meaning in sentences is expressed through various suffixes of nouns, verbs, and other parts of speech. In this article, we present a neural semantic analysis of Uzbek language texts based on a set of trees created using the Universal Dependencies (UD) corpus. This corpus contains 686 sentences and 7,950 tokens, with an average of 11.6 tokens per sentence. We construct a graph-based parser that employs a two-stage architecture - a BiLSTM-based contextual encoder combined with a biaffine function that integrates head and dependent projections.
| Mualliflar | Matlatipov, Sanatbek, Fayzullayev, Xurshid |
|---|---|
| Jurnal | Al-Farg'oniy avlodlari |
| Nashr sanasi | 2025-10-08 |
| Son | 3 |
| Betlar | 135-138 |
| Til | Rus |
корпус универсального дерева зависимостей, Universal Dependency treebank, Uzbek language, kam resursli tillar universal bog‘liqliklar, o‘zbek tili, neyron semantik tahlil
The article considers the problem of extracting characteristic features of handwritten text images, which is an important stage in the development of personal identification systems based on the analysis of handwritten…
This article discusses a method for detecting false positives against a biometric facial recognition system based on deep convolutional neural networks. The proposed method is designed to detect printed false positives…
Abstract: The article examines the methods of modeling facial elements of an animated character and the problem of their animation, as well as proposes approaches to its solution. Using three-dimensional modeling…
Drones equipped with Global Navigation Satellite Systems have transformed modern geospatial mapping, precision agriculture, and surveying. Standard Global Positioning System technology provides meter-level accuracy, but…
This article analyzes the role of Software Configuration Management (SCM) and security tool integration within Continuous Integration/Continuous Deployment (CI/CD) pipelines. It is determined that embedding…
In this article, the bending process of a rectangular plate under external load is studied both theoretically and practically. The deformation process is based on the theory of elasticity and involves a structural…
The article proposes an algorithm for automatic and interactive restoration of defects in archival images. The proposed method improves image quality, reduces noise and distortions, and accelerates the restoration…
This study analyzes geometry and short-time hydration of two wheat varieties from Uzbekistan, “Asr” and “Alekseevich.” Grain dimensions were measured by digital caliper, microstructure examined microscopically, and…
Abstract. This paper presents a methodological framework for classifying network traffic anomalies, detailing the relationships between their sources, manifestation areas, and characteristic features. Optimized…
In this study, digital image processing and a convolutional neural network (CNN) were integrated to automatically detect mitral stenosis based on 32 echocardiogram videos. By applying data augmentation, the training…