Overview of methods for automated creation of ontologies for scientific domains

Context and relevance. Modern intelligent systems for processing and analyzing the semantic content of industry texts work with textual information containing thousands of classes of objects and an unlimited number of semantic relationships. All this knowledge about high-tech industries can be implemented in ontological reference books. The need for automated generation of such tools is an urgent task, including to ensure researchers' access to scientific resources. Nevertheless, the manual creation of ontologies for high-tech industries is extremely time-consuming, and the use of «raw» Large Language Models (LLM) creates problems of «hallucinations» and data heterogeneity. Thus, there is a need to use hybrid methods for automated construction of industry ontologies that combine the accuracy of linguistic analysis with the scalability of LLM. Objective. To investigate the existing methods of creating ontologies and methods of their comparison, to consider the problems that arise in this case, and to propose new methods for the automated creation of industry-specific ontologies of subject areas of science. Hypothesis. The integration of linguistic statistical methods, the method of conceptual phraseological analysis and specialized LLM in a single cycle will increase the completeness and accuracy of automatic extraction of concepts and generic relationships between them from scientific and technical documentation, while reducing the level of «hallucinations» and the heterogeneity of the resulting ontologies. Methods and materials. The research is based on the analysis of four groups of methods: Lexical Syntax Patterns (LSP), statistical methods of frequency analysis, Deep Learning methods (including LLM) and hybrid approaches. To verify the proposed approach, an array of 3,000 full-text documents on aviation topics has been collected. Results. As a result of the analysis of existing methods for constructing ontologies, their key disadvantages have been identified. Preliminary studies have shown that the proposed method of automated creation of industry-specific ontological reference books is workable and will provide an opportunity to solve the task with minimal effort. An algorithm for creating industry-specific ontologies has been developed, in which LLMs are used not in isolation, but in conjunction with the rules of linguistic analysis. Conclusions. It is shown that none of the existing classes of methods for automatic ontology construction is universal: linguistic patterns require manual adaptation, statistics are limited in accuracy, and neural network models suffer from «hallucinations». The developed hybrid approach, unlike well-known solutions, allows LLM to be applied not as a «black box», but in conjunction with linguistic rules, providing a closed loop of iterative ontology refinement. The prospects for further work include scaling the approach to other scientific fields and integration with existing knowledge bases. The results of the work will be implemented in the technological process of VINITI RAS to solve the problems of text analysis in various subject areas.

1. Захарова, И. В. (2009). Математическая модель семантического поиска с использованием онтологического подхода: Автореф. дис. канд. физ.-мат. наук. Челябинский государственный университет. Челябинск.
   Zakharova, I. V. (2009). Mathematical model of semantic search using an ontological approach: Extended abstr. Diss. Cand. Sci. (Ph.-Mat.). Chelyabinsk State University. Chelyabinsk. (In Russ.).
2. Кравченко, Д.Ю., Кравченко, Ю.А., Марков, В.В. Гибридный биоинспирированный алгоритм отображения онтологий в задачах извлечения и управления знаниями. — Известия ЮФУ. Технические науки. 2020. — Ростов-на-Дону: ЮФУ, 2020. — с. 16—28.
   Kravchenko, D.Yu., Kravchenko, Yu.A., Markov, V.V. Hybrid bioinspired algorithm for mapping ontologies in knowledge extraction and management tasks. — Izvestiya YuFU. Tekhnicheskie nauki. 2020. — Rostov-na-Donu: YuFU, 2020. — pp. 16—28. (In Russ.).
3. Лукашевич В.Н. (2016). Модели и методы автоматического анализа текстов на основе лингвистических онтологий в информационно-аналитических системах: Автореф. дис. докт. тех. наук. Нижегородский государственный технический университет им. Р.Е. Алексеева. Нижний Новгород.
   Lukashevich V.N. (2016). Models and methods of automatic text analysis based on linguistic ontologies in information and analytical systems: Extended abstr. Diss. Dr. Sci. (Techn.). Nizhny Novgorod State Technical University named after R.E. Alekseev. Nizhnii Novgorod. (In Russ.).
4. Рогушина, Ю.В. Сопоставление семантических информационных ресурсов Web на основе онтологического анализа. International Journal «Information Technologies & Knowledge». — Vol. 11, N. 1. — 2017. — с. 49—71.
   Rogushina, Yu.V. Comparison of semantic Web information resources based on ontological analysis. International Journal «Information Technologies & Knowledge». — Vol. 11, N. 1. — 2017. — pp. 49—71. (In Russ.).
5. Сидорова, Е.А. Иванов, А.И., Овчинникова, К.А. Извлечение информации из текстов на основе онтологии и больших языковых моделей. Онтология проектирования. — № 1, Т. 15. — 2025. — с. 114—129.
   Sidorova, E.A. Ivanov, A.I., Ovchinnikova, K.A. Information extraction from texts based on ontology and large language models. Ontologiya proektirovaniya. — № 1, T. 15. — 2025. — pp. 114—129. (In Russ.).
6. Хорошилов, А.А., Никитин, Ю. В., Будзко, В.И. Автоматическое создание формализованного представления смыслового содержания неструктурированных текстовых сообщений СМИ и социальных сетей. Системы высокой доступности. — 2014. — Т. 10, № 3. — С. 52—69.
   Khoroshilov, A.A., Nikitin, Yu. V., Budzko, V.I. Automatic creation of a formalized representation of the semantic content of unstructured text messages in the media and social networks. Sistemy vysokoi dostupnosti. — 2014. — T. 10, № 3. — P. 52—69. (In Russ.).
7. Хорошилов, А.А., Кан, А. В., Филиппов, Г.В. Методы автоматического формирования комплекса онтологических справочников по авиакосмической отрасли. Научно-технический вестник Поволжья. № 5. — 2024. — Казань: ООО «Рашин Сайнс», 2024. — с. 150—154.
   Khoroshilov, A.A., Kan, A. V., Filippov, G.V. Methods of automatic formation of a complex of ontological reference books on the aerospace industry. Nauchno-tekhnicheskii vestnik Povolzh'ya. № 5. — 2024. — Kazan': OOO «Rashin Sains», 2024. — pp. 150—154. (In Russ.).
8. Чуднов, И.И. Нейро-символические гибридные системы для динамического управления знаниями. КОД науки — исследования молодых ученых. № 5 (73). — 2025. — Москва: МГПУ, 2025.
   Chudnov, I.I. Neuro-symbolic hybrid systems for dynamic knowledge management. KOD nauki — issledovaniya molodykh uchenykh. № 5 (73). — 2025. — Moskva: MGPU, 2025. (In Russ.).
9. Gangemi, A., Presutti, V. Ontology Design Patterns. Handbook on Ontologies. — 2009. — pp. 221—243.
10. Ghidalia, S. Combining Machine Learning and Ontology: A Systematic Literature Review. — 2023. URL: https://ar5iv.labs.arxiv.org/html/2401.07744 (дата обращения: 20.12.2025).
11. Gruber T. R. Toward principles for the design of ontologies used for knowledge sharing. International Journal of Human—Computer Studies. — 1995. — Т. 43. — № 5—6. — pp. 907—928.
12. Kukreja, S. End-to-End Ontology Learning Pipeline for Technical Documents. — 2025. URL: https://github.com/itssnehin/Ontology-Learning (дата обращения: 20.12.2025).
13. Lv, Q., Jiang, C., Li, H. Solving Ontology Meta—Matching Problem Through an Evolutionary Algorithm with Approximate Evaluation Indicators and Adaptive Selection Pressure. IEEE Access. — Vol. 9, 2021. — pp. 3046—3064. DOI: 10.1109/ACCESS.2020.3047875.
14. Maedche, A., Staab, S. Measuring Similarity between Ontologies Knowledge Engineering and Knowledge Management: Ontologies and the Semantic Web. Proceedings of the 13th International Conference on Knowledge Engineering and Knowledge Management, EKAW02. — Vol. 2473 of LNAI, Berlin, Springer Verlag. — 2002.
15. Sadirmekova, Z. et al. Approach to automating the construction and completion of ontologies in a scientific subject field. International Journal of Electrical and Computer Engineering. Vol.14, No. 3. — 2024. — p. 3064—3072.
16. Sivaramakrishnan, R. G., Suchithra, R. Automatic Relationship Construction in Domain Ontology Engineering using Semantic and Thematic Graph Generation Process and Convolution Neural Network. International Journal of Recent Technology and Engineering. — Vol. 8. — I.3. — 2019. — pp. 4602—4610.