Models for Automatic Recognition of Onomastic Units (Proper Nouns) in the Uzbek Language

This article explores the types of onomastic units, their linguistic analysis, their role within various language units, and their macro and micro scales. The classification of onomastic units, their functional characteristics, and their examination based on modern linguistics—particularly computational linguistics—are discussed. Additionally, the concept of onomastic units and Named Entity Recognition (NER) is studied, compared, and analyzed. The methods for identifying three major types of NER objects in texts are examined. The lexical-semantic features of onomastic units in the Uzbek language corpus are analyzed, and the effectiveness of NER approaches in their automatic extraction is evaluated. The main goal of the article is to study naming units in Uzbek at the intersection of corpus linguistics and computational linguistics and to highlight the possibilities of applying modern technological methods for their identification.

Перевод пока недоступен