Information and communication and chemical technologies

Vol. 2 No. 27 (2025) / 2025-06-28 / Number of views: 225

EXTRACTING SEMANTIC DATA FROM TEXTS BASED ON LARGE LANGUAGE MODELS

Authors

Astana International University
https://orcid.org/0009-0001-6106-8776
Astana International University
https://orcid.org/0000-0002-8964-3891
L.N. Gumilyov ENU
https://orcid.org/0000-0002-9162-6791
L.N. Gumilyov ENU
https://orcid.org/0000-0002-8967-2625
L.N. Gumilyov ENU
https://orcid.org/0000-0001-9843-6125
Astana International University
https://orcid.org/0009-0008-6374-6447

Keywords

data extraction, LLM, ChatGPT, semantic web, OpenAI API, оntological model

Link to DOI:

https://doi.org/10.58805/kazutb.v.2.27-902

How to quote

Dauletkaliyeva, A., et al. “EXTRACTING SEMANTIC DATA FROM TEXTS BASED ON LARGE LANGUAGE MODELS”. Vestnik KazUTB, vol. 2, no. 27, June 2025, doi:10.58805/kazutb.v.2.27-902.

Abstract

There are several interrelated stages in the process of applying the technology. First, information with semantic meaning is selected from the text. Then they are brought into a certain structure and included in the ontological model. At the last stage, semantic connections are established between these data as a result of the formation of the internal structure of the ontological system.

In addition, the method was tested on an ontological model describing the administrative and geographical features of Kazakhstan. Experience has shown that this approach can be effectively applied not only in a specific field, but also in other areas such as healthcare, multidimensional text data analysis.

The results of the study showed that the proposed approach makes it possible to systematize complex text structures and add them to the knowledge base. In this field, this method can play a particularly important role in the development of intelligent systems, especially in projects designed for the automatic processing and interpretation of complex knowledge.