ellibsЭлектронные библиотекиRussian Digital Libraries Journal1562-5419Казанский (Приволжский) федеральный университет10.26907/1562-5419-2025-28-6-1306-1323ellibs-621Research ArticleСтатьиФормирование структурированных представлений научных журналов для интеграции в граф знаний и семантического поискаFormation of Structured Representations of Scientific Journals for Integration into a Knowledge Graph and Semantic SearchАтаеваОльга МуратовнаAtaevaOlga Muratovnaoataeva@frccsc.ruКобукМихаил ГеннадьевичKobukMikhail Gennadievichmikhail.kobuk@mail.ruФедеральный исследовательский центр «Информатика и управление» Российской академии наукFederal Research Center “Computer Science and Control” of the Russian Academy of SciencesМосковский университет имени С.Ю. ВиттеS. Witte University of Moscow20251912202528613061323Copyright © Атаева О.М., Кобук М.Г., 20252025Атаева О.М., Кобук М.Г.Ataeva O.M., Kobuk M.G.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://ellibs.elpub.ru/jour/article/view/621

Работа посвящена проблеме развития библиотеки научных предметных областей SciLibRu, как продолжения семантического описания научных трудов проекта LibMeta. В основе этой библиотеки лежит концептуальная модель данных, структура и семантика которой сформированы на принципах онтологического моделирования. Такой подход обеспечивает строгое описание предметной области, формализацию взаимосвязей между сущностями и возможность дальнейшего автоматизированного анализа данных. Целью настоящего исследования были разработка и экспериментальное применение методов структуризации содержимого научных журналов в формате LaTeX для их интеграции в онтологию библиотеки и обеспечения семантического поиска. Предложен алгоритм трансляции в формат XML данных, представленных множеством файлов, для интеграции в онтологию библиотеки. Реализован модуль векторного поиска, основанный на вычислении эмбеддингов с использованием языковых моделей. Выявлены закономерности распределения эмбеддингов и факторы, влияющие на точность ранжирования результатов поиска. Проведено тестирование двух названых компонентов. Разработанный метод составляет основу для автоматического включения содержимого научных журналов в граф знаний SciLibRu и создания обучающих корпусов для языковых моделей, ограниченных рамками научных предметных областей. Полученные результаты способствуют развитию систем навигации по графу знаний журналов, а также рекомендательных механизмов и инструментов интеллектуального поиска по русскоязычным научным текстам.

This paper examines the development of the SciLibRu library of scientific subject areas, as a continuation of the semantic description of scientific works from the library LibMeta project. This library is based on a conceptual data model, the structure and semantics of which are formed based on the principles of ontological modeling. This approach ensures a strict description of the subject area, formalization of the relationships between entities, and the possibility of further automated data analysis. The goal of the study is to develop and experimentally apply methods for structuring scientific journal data in LaTeX format for their integration into the library ontology and to support semantic search. An algorithm for translating data represented by multiple files into XML format is proposed for integration into the library ontology. A vector search module based on embedding calculation using language models is implemented. Patterns in the distribution of embeddings and factors influencing the accuracy of search results ranking are identified. Testing of the two components is conducted. The developed method forms the basis for automatically incorporating scientific journal data into the SciLibRu knowledge graph and creating training corpora for language models limited to scientific subject areas. The obtained results contribute to the development of journal knowledge graph navigation systems, recommendation engines, and intelligent search tools for Russian-language scientific texts.

полуструктурированные данныеонтология текстаLaTeXвекторное представление текстаполнотекстовый поисксемантический поискsemi-structured datatext structuringLaTeXvector representations of textfull-text searchsemantic searchReferencesHoftich M. TEX4ht: LATEX to Web Publishing // TUGboat. 2019. Vol. 40, No. 1. P. 76–81.Hoftich M. TEX4ht: LATEX to Web Publishing // TUGboat. 2019. Vol. 40, No. 1. P. 76–81.Frankston C. et al. Using HTML Papers on arXiv: Why It’s Important, and How We Made It Happen // arXiv preprint 2024. https://doi.org/10.48550/arXiv.2402.08954 (In Russ.)Frankston C. et al. Using HTML Papers on arXiv: Why It’s Important, and How We Made It Happen // arXiv preprint 2024. https://doi.org/10.48550/arXiv.2402.08954 (In Russ.)Serebryakov V.A., Galochkin M.P., Gonchar D.R., Furugyan M.G. Theory and Implementation of Programming Languages. 2nd ed. Moscow: MZ-Press, 2006. 352 p. (In Russ.)Serebryakov V.A., Galochkin M.P., Gonchar D.R., Furugyan M.G. Theory and Implementation of Programming Languages. 2nd ed. Moscow: MZ-Press, 2006. 352 p. (In Russ.)Hopcroft J., Motwani R., Ullman J. Introduction to Automata Theory, Languages, and Computation. Moscow: Williams, 2002. 528 p. (In Russ.)Hopcroft J., Motwani R., Ullman J. Introduction to Automata Theory, Languages, and Computation. Moscow: Williams, 2002. 528 p. (In Russ.)Aho A.V., Lam M.S., Sethi R., Ullman J.D. Compilers: Principles, Techniques, and Tools. 2nd ed. Moscow: Williams, 2008. 1184 p. (In Russ.)Aho A.V., Lam M.S., Sethi R., Ullman J.D. Compilers: Principles, Techniques, and Tools. 2nd ed. Moscow: Williams, 2008. 1184 p. (In Russ.)Mikolov T., Sutskever I., Chen K., Corrado G., Dean J. Distributed Representations of Words and Phrases and their Compositionality // Advances in Neural Information Processing Systems (NIPS 26). 2013. P. 3111–3119. URL: https://dl.acm.org/doi/10.5555/2999792.2999959 (date accessed: 08.11.2025)Mikolov T., Sutskever I., Chen K., Corrado G., Dean J. Distributed Representations of Words and Phrases and their Compositionality // Advances in Neural Information Processing Systems (NIPS 26). 2013. P. 3111–3119. URL: https://dl.acm.org/doi/10.5555/2999792.2999959 (date accessed: 08.11.2025)Pennington J., Socher R., Manning C. GloVe: Global Vectors for Word Representation // Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2014. P. 1532–1543. https://doi.org/10.3115/v1/D14-1162Pennington J., Socher R., Manning C. GloVe: Global Vectors for Word Representation // Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2014. P. 1532–1543. https://doi.org/10.3115/v1/D14-1162Joulin A., Grave E., Bojanowski P., Mikolov T. Bag of Tricks for Efficient Text Classification // Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers. Valencia, Spain, April 2017. P. 427–431. https://doi.org/10.18653/v1/E17-2068Joulin A., Grave E., Bojanowski P., Mikolov T. Bag of Tricks for Efficient Text Classification // Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers. Valencia, Spain, April 2017. P. 427–431. https://doi.org/10.18653/v1/E17-2068Feng F., Yang Y., Cer D., Arivazhagan N., Wang W. Language-agnostic BERT Sentence Embedding // Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL). Dublin, Ireland, May 2022. Р. 878–891. https://doi.org/10.18653/v1/2022.acl-long.62Feng F., Yang Y., Cer D., Arivazhagan N., Wang W. Language-agnostic BERT Sentence Embedding // Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL). Dublin, Ireland, May 2022. Р. 878–891. https://doi.org/10.18653/v1/2022.acl-long.62Zmitrovich D. et al. A Family of Pretrained Transformer Language Models for Russian // arXiv preprint 2023. https://doi.org/10.48550/arXiv.2309.10931Zmitrovich D. et al. A Family of Pretrained Transformer Language Models for Russian // arXiv preprint 2023. https://doi.org/10.48550/arXiv.2309.10931Kuratov Y., Arkhipov M. Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language // arXiv preprint 2019. https://doi.org/10.48550/arXiv.1905.07213Kuratov Y., Arkhipov M. Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language // arXiv preprint 2019. https://doi.org/10.48550/arXiv.1905.07213Nikolich A., Puchkova A. Fine-tuning GPT-3 for Russian Text Summarization // arXiv preprint 2021. https://doi.org/10.48550/arXiv.2108.03502Nikolich A., Puchkova A. Fine-tuning GPT-3 for Russian Text Summarization // arXiv preprint 2021. https://doi.org/10.48550/arXiv.2108.03502Kutuzov A., Kuzmenko E. WebVectors: A Toolkit for Building Web Interfaces for Vector Semantic Models // In: Ignatov D. et al. (Eds.) Analysis of Images, Social Networks and Texts (AIST 2016). Communications in Computer and Information Science. Vol. 661. Springer, Cham, 2017. https://doi.org/10.1007/978-3-319-52920-2_15Kutuzov A., Kuzmenko E. WebVectors: A Toolkit for Building Web Interfaces for Vector Semantic Models // In: Ignatov D. et al. (Eds.) Analysis of Images, Social Networks and Texts (AIST 2016). Communications in Computer and Information Science. Vol. 661. Springer, Cham, 2017. https://doi.org/10.1007/978-3-319-52920-2_15Kasenchak R.T. What is Semantic Search? and Why Is It Important? // Information Services and Use. 2019. Vol. 39. No. 3. Р. 205–213. https://doi.org/10.3233/ISU-190045Kasenchak R.T. What is Semantic Search? and Why Is It Important? // Information Services and Use. 2019. Vol. 39. No. 3. Р. 205–213. https://doi.org/10.3233/ISU-190045Shelke P. et al. A Systematic and Comparative Analysis of Semantic Search Algorithms // International Journal on Recent and Innovation Trends in Computing and Communication. 2023. Vol. 11, No. 11s. P. 222–229. https://doi.org/10.17762/ijritcc.v11i11s.8094Shelke P. et al. A Systematic and Comparative Analysis of Semantic Search Algorithms // International Journal on Recent and Innovation Trends in Computing and Communication. 2023. Vol. 11, No. 11s. P. 222–229. https://doi.org/10.17762/ijritcc.v11i11s.8094Weckmüller D., Dunkel A., Burghardt D. Embedding-Based Multilingual Semantic Search for Geo-Textual Data in Urban Studies // Journal of Geovisualization and Spatial Analysis. 2025. Vol. 9. No. 31. P. 1–18. https://doi.org/10.1007/s41651-025-00232-5Weckmüller D., Dunkel A., Burghardt D. Embedding-Based Multilingual Semantic Search for Geo-Textual Data in Urban Studies // Journal of Geovisualization and Spatial Analysis. 2025. Vol. 9. No. 31. P. 1–18. https://doi.org/10.1007/s41651-025-00232-5Siddharth Pratap Singh. Vector Search in the Era of Semantic Understanding: A Comprehensive Review of Applications and Implementations // International Journal of Computer Engineering and Technology. 2024. Vol. 15. No. 6. P. 1794–1805. https://doi.org/10.34218/IJCET_15_06_153Siddharth Pratap Singh. Vector Search in the Era of Semantic Understanding: A Comprehensive Review of Applications and Implementations // International Journal of Computer Engineering and Technology. 2024. Vol. 15. No. 6. P. 1794–1805. https://doi.org/10.34218/IJCET_15_06_153Zhou Y. et al. Problems with Cosine as a Measure of Embedding Similarity for High Frequency Words // 2022. https://doi.org/10.48550/arXiv.2205.05092Zhou Y. et al. Problems with Cosine as a Measure of Embedding Similarity for High Frequency Words // 2022. https://doi.org/10.48550/arXiv.2205.05092Healy J., McInnes L. Uniform manifold approximation and projection // Nature Reviews Methods Primers. 2024, Vol. 4. No. 82. P. 1–15. https://doi.org/10.1038/s43586-024-00363-xHealy J., McInnes L. Uniform manifold approximation and projection // Nature Reviews Methods Primers. 2024, Vol. 4. No. 82. P. 1–15. https://doi.org/10.1038/s43586-024-00363-x

The authors declare that there are no conflicts of interest present.