IDENTIFICATION OF NAMED ENTITIES IN KAZAKH TEXTS USING TRANSFORMER MODELS

This paper explores Named Entity Recognition (NER) in the Kazakh language using transformer-based models. NER is a subfield of Natural Language Processing (NLP) that involves the automatic identification of named entities in textual data and their classification into predefined categories. A review of previous studies indicates that further research is needed on this topic in Kazakh texts. Scientific works in the field of information technology were taken as textual data, and in the preparation of dataset, along with named entities, such as the names of people, names of institutions, places of location, terms in the field were marked up in IBO2 format. For the recognition of named entities, the transformer model of the spacy library and the large Llama language model were considered. To solve the task, the internal structural blocks of both models were fully described, a formal description of the implementation of the NER task was given and their fine-tuning was performed. The models were trained on a prepared dataset and various tests were performed. Obtained results are compared with the indicators of other studies and a comparative analysis is presented.