ellibsЭлектронные библиотекиRussian Digital Libraries Journal1562-5419Казанский (Приволжский) федеральный университет10.26907/1562-5419-2025-28-6-1481-1519ellibs-629Research ArticleСтатьиАвтоматические и полуавтоматические методы построения графа знаний предметной области и расширения онтологииAutomatic and Semi-Automatic Methods for Domain Knowledge-Graph Construction and Ontology ExpansionХаловАндрей ПетровичKhalovAndrey Petrovichkhalov.a@phystech.eduАтаеваОльга МуратовнаAtaevaOlga Muratovnaoataeva@frccsc.ruМосковский физико-технический институтMoscow Institute of Physics and TechnologyФедеральный исследовательский центр «Информатика и управление» Российской академии наукFederal Research Center “Computer Science and Control” of the Russian Academy of Sciences20251912202528614811519Copyright © Халов А.П., Атаева О.М., 20252025Халов А.П., Атаева О.М.Khalov A.P., Ataeva O.M.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/629

Рассмотрен цикл построения графа знаний и расширения онтологии для специальной предметной области, описывающей процесс управления потоками данных в службах информационной поддержки. Предложена методика формирования корпуса данных для наполнения онтологии с автоматической псевдоразметкой, включающей специальные категории для фиксации ранее не представленных классов и отношений. Обучена специализированная модель извлечения именованных сущностей на корпусе данных объемом 3 млн токенов с 92 метками. Результаты были использованы для интеграции извлеченных фактов, что увеличило граф знаний до 0.98 млн триплетов, при этом коэффициент расширения графа (отношение общего числа фактов к явным триплетам) увеличился с 2.65 до 3.52 при сохранении логической согласованности. Наборы токенов с одинаковыми метками были преобразованы в устойчивые семантические множества, что позволило полуавтоматически расширить онтологию. В онтологию добавлены 12 новых классов, которые были извлечены из неструктурированных текстовых данных. Показан прикладной пример запросов и дальнейшей аналитики.

We present a combined pipeline for knowledge-graph construction and ontology expansion. The approach builds a BIO-tagged corpus via fully automatic LLM-based pseudo-annotation and introduces dedicated UNK reserve categories to capture previously unseen classes and relations. A specialized NER/RE model is trained on a 3-million-token dataset with 92 labels. The model exhibits a conservative quality profile – high precision with moderate recall – suited for safe graph enrichment: integrating the extracted facts expands the graph to ~0.98 million triples, while the expansion ratio (total inferred facts to explicit triples) increases from 2.65 to 3.52, with logical consistency preserved. UNK label pools are converted into stable synsets, enabling semiautomatic ontology expansion; 12 new classes derived from unstructured texts were added. We also demonstrate practical value for querying and analytics using an LLM + SPARQL setup.

онтологияDOLCEграф знанийNERBIO-разметкаRDF/OWLSPARQLontologyDOLCEknowledge graphNERBIO taggingRDF/OWLSPARQLReferencesBorgo S. et al. DOLCE: A descriptive ontology for linguistic and cognitive engineering // Applied Ontology. 2023. Vol. 17, No. 1. Р. 45–69.Borgo S. et al. DOLCE: A descriptive ontology for linguistic and cognitive engineering // Applied Ontology. 2023. Vol. 17, No. 1. Р. 45–69.IT Service Management Ontology (ITSMO). Canonical resolver; catalog entry in LOV “IT Service Management Ontology (itsmo)”. https://w3id.org/itsmo; ontology.it; lov.linkeddata.es (Accessed: 08 August 2025).IT Service Management Ontology (ITSMO). Canonical resolver; catalog entry in LOV “IT Service Management Ontology (itsmo)”. https://w3id.org/itsmo; ontology.it; lov.linkeddata.es (Accessed: 08 August 2025).Khalov A., Ataeva O. Automating Ontology Mapping in IT Service Management: A DOLCE and ITSMO Integration // Data Science Journal. 2025. Vol. 24. Р. 23. https://doi.org/10.5334/dsj-2025-023Khalov A., Ataeva O. Automating Ontology Mapping in IT Service Management: A DOLCE and ITSMO Integration // Data Science Journal. 2025. Vol. 24. Р. 23. https://doi.org/10.5334/dsj-2025-023Gruber T.R. A translation approach to portable ontology specifications // Knowledge Acquisition. 1993. Vol. 5, No. 2. Р. 199–220. https://doi.org/10.1006/knac.1993.1008Gruber T.R. A translation approach to portable ontology specifications // Knowledge Acquisition. 1993. Vol. 5, No. 2. Р. 199–220. https://doi.org/10.1006/knac.1993.1008Gruber T.R. Toward principles for the design of ontologies used for knowledge sharing // International Journal of Human-Computer Studies. 1995. Vol. 43, No. 5–6. Р. 907–928. https://doi.org/10.1006/ijhc.1995.1081Gruber T.R. Toward principles for the design of ontologies used for knowledge sharing // International Journal of Human-Computer Studies. 1995. Vol. 43, No. 5–6. Р. 907–928. https://doi.org/10.1006/ijhc.1995.1081Smith B. Ontology (Science) // Formal Ontology in Information Systems, IOS Press, 2008. Р. 21–35. https://doi.org/10.1038/npre.2008.2027.2Smith B. Ontology (Science) // Formal Ontology in Information Systems, IOS Press, 2008. Р. 21–35. https://doi.org/10.1038/npre.2008.2027.2Studer R., Benjamins V.R., Fensel D. Knowledge Engineering: Principles and Methods // Data & Knowledge Engineering. 1998. Vol. 25, No. 1–2. Р. 161–197. https://doi.org/10.1016/S0169-023X(97)00056-6Studer R., Benjamins V.R., Fensel D. Knowledge Engineering: Principles and Methods // Data & Knowledge Engineering. 1998. Vol. 25, No. 1–2. Р. 161–197. https://doi.org/10.1016/S0169-023X(97)00056-6Hogan A., Blomqvist E., Cochez M. et al. Knowledge Graphs. Morgan & Claypool Publishers, 2021. 257 p.Hogan A., Blomqvist E., Cochez M. et al. Knowledge Graphs. Morgan & Claypool Publishers, 2021. 257 p.Barrasa J., Webber J. Building Knowledge Graphs: A Practitioner's Guide. O'Reilly Media, 2023. 250 p.Barrasa J., Webber J. Building Knowledge Graphs: A Practitioner's Guide. O'Reilly Media, 2023. 250 p.El Yamami A. et al. An ontological representation of ITIL framework service level management process // Proceedings of the 3rd International Conference on Signals, Distributed Systems and Artificial Intelligence (SDSAI 2018). 2019. Springer.El Yamami A. et al. An ontological representation of ITIL framework service level management process // Proceedings of the 3rd International Conference on Signals, Distributed Systems and Artificial Intelligence (SDSAI 2018). 2019. Springer.Valiente M.-C., Vicente-Chicote C., Rodriguez D. An Ontology-Based and Model-Driven Approach for Designing IT Service Management Systems // Int. J. of Service Science, Management, Engineering, and Technology. 2011. Vol. 2 (2). P. 65–81.Valiente M.-C., Vicente-Chicote C., Rodriguez D. An Ontology-Based and Model-Driven Approach for Designing IT Service Management Systems // Int. J. of Service Science, Management, Engineering, and Technology. 2011. Vol. 2 (2). P. 65–81.Miwa M., Bansal M. End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures // Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2016. Р. 1105–1116. Berlin, Germany: Association for Computational Linguistics. https://doi.org/10.18653/v1/P16-1105Miwa M., Bansal M. End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures // Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2016. Р. 1105–1116. Berlin, Germany: Association for Computational Linguistics. https://doi.org/10.18653/v1/P16-1105Xu J., Zhang Z., Friedman T., Liang Y., Van den Broeck G. A Semantic Loss Function for Deep Learning with Symbolic Knowledge // Proceedings of the 35th International Conference on Machine Learning (ICML). PMLR, 2018. Vol. 80. Р. 5502–5511. URL: https://proceedings.mlr.press/v80/xu18h.htmlXu J., Zhang Z., Friedman T., Liang Y., Van den Broeck G. A Semantic Loss Function for Deep Learning with Symbolic Knowledge // Proceedings of the 35th International Conference on Machine Learning (ICML). PMLR, 2018. Vol. 80. Р. 5502–5511. URL: https://proceedings.mlr.press/v80/xu18h.htmlSun K., Zhang R., Mensah S., Mao Y., Liu X. Learning Implicit and Explicit Multi-task Interactions for Information Extraction // ACM Transactions on Information Systems. 2023. Vol. 41, No. 2. Р. 1–29. https://doi.org/10.1145/3533020Sun K., Zhang R., Mensah S., Mao Y., Liu X. Learning Implicit and Explicit Multi-task Interactions for Information Extraction // ACM Transactions on Information Systems. 2023. Vol. 41, No. 2. Р. 1–29. https://doi.org/10.1145/3533020Giunchiglia E., Lukasiewicz T. Coherent Hierarchical Multi-label Classification Networks // Advances in Neural Information Processing Systems 33 (NeurIPS 2020). 2020. URL: https://proceedings.neurips.cc/paper/2020/file/ 6dd4e10e3296fa63738371ec0d5df818-Paper.pdfGiunchiglia E., Lukasiewicz T. Coherent Hierarchical Multi-label Classification Networks // Advances in Neural Information Processing Systems 33 (NeurIPS 2020). 2020. URL: https://proceedings.neurips.cc/paper/2020/file/ 6dd4e10e3296fa63738371ec0d5df818-Paper.pdfYu J., Bohnet B., Poesio M. Named Entity Recognition as Dependency Parsing // Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL). 2020. Р. 6470–6476. https://doi.org/10.18653/v1/2020.acl-main.577Yu J., Bohnet B., Poesio M. Named Entity Recognition as Dependency Parsing // Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL). 2020. Р. 6470–6476. https://doi.org/10.18653/v1/2020.acl-main.577Lu Y., Liu Q., Dai D., Xiao X., Lin H., Han X., Sun L., Wu H. Unified Structure Generation for Universal Information Extraction // Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022. Р. 5755–5772. https://doi.org/10.18653/v1/2022.acl-long.395Lu Y., Liu Q., Dai D., Xiao X., Lin H., Han X., Sun L., Wu H. Unified Structure Generation for Universal Information Extraction // Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022. Р. 5755–5772. https://doi.org/10.18653/v1/2022.acl-long.395Gururangan S., Marasović A., Swayamdipta S., Lo K., Beltagy I., Downey D., Smith N. A. Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks // Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL). 2020. Р. 8342–8360. https://doi.org/10.18653/v1/2020.acl-main.740Gururangan S., Marasović A., Swayamdipta S., Lo K., Beltagy I., Downey D., Smith N. A. Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks // Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL). 2020. Р. 8342–8360. https://doi.org/10.18653/v1/2020.acl-main.740Brown T.B. et al. Language Models are Few-Shot Learners // Advances in Neural Information Processing Systems. 2020. Vol. 33. URL: https://proceedings.neurips.cc/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdfBrown T.B. et al. Language Models are Few-Shot Learners // Advances in Neural Information Processing Systems. 2020. Vol. 33. URL: https://proceedings.neurips.cc/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdfAlizadeh M., Kubli M., Samei Z., Dehghani S., Zahedivafa M., Bermeo J.D., Korobeynikova M., Gilardi F. Open-source LLMs for text annotation: a practical guide for model setting and fine-tuning // Journal of Computational Social Science. 2025. Vol. 8. Article 17. https://doi.org/10.1007/s42001-024-00345-9Alizadeh M., Kubli M., Samei Z., Dehghani S., Zahedivafa M., Bermeo J.D., Korobeynikova M., Gilardi F. Open-source LLMs for text annotation: a practical guide for model setting and fine-tuning // Journal of Computational Social Science. 2025. Vol. 8. Article 17. https://doi.org/10.1007/s42001-024-00345-9Eiras F. et al. Position: Near to Mid-term Risks and Opportunities of Open-Source Generative AI // Proceedings of the 41st International Conference on Machine Learning (ICML 2024). Proceedings of Machine Learning Research. 2024. Vol. 235. Р. 12348–12370. URL: https://proceedings.mlr.press/v235/eiras24b.htmlEiras F. et al. Position: Near to Mid-term Risks and Opportunities of Open-Source Generative AI // Proceedings of the 41st International Conference on Machine Learning (ICML 2024). Proceedings of Machine Learning Research. 2024. Vol. 235. Р. 12348–12370. URL: https://proceedings.mlr.press/v235/eiras24b.htmlTjong Kim Sang, E. F., De Meulder F. Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition. In: HLT-NAACL 2003 (CoNLL-2003).Tjong Kim Sang, E. F., De Meulder F. Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition. In: HLT-NAACL 2003 (CoNLL-2003).Zhang B., May J., Nothman J., Knight K., Ji H. Cross-lingual Name Tagging and Linking for 282 Languages. ACL 2017.Zhang B., May J., Nothman J., Knight K., Ji H. Cross-lingual Name Tagging and Linking for 282 Languages. ACL 2017.Derczynski, L. et al. Results of the WNUT2017 Shared Task on Novel and Emerging Entity Recognition. W-NUT 2017 (ACL Workshop).Derczynski, L. et al. Results of the WNUT2017 Shared Task on Novel and Emerging Entity Recognition. W-NUT 2017 (ACL Workshop).Brown T.B. et al. Language Models are Few-Shot Learners // Advances in Neural Information Processing Systems. 2020. Vol. 33.Brown T.B. et al. Language Models are Few-Shot Learners // Advances in Neural Information Processing Systems. 2020. Vol. 33.Campello R.J.G.B., Moulavi D., Sander J. Hierarchical density estimates for data clustering, visualization, and outlier detection // ACM Transactions on Knowledge Discovery from Data (TKDD). 2015. Vol. 10 (1). P. 5. https://doi.org/10.1145/2733381Campello R.J.G.B., Moulavi D., Sander J. Hierarchical density estimates for data clustering, visualization, and outlier detection // ACM Transactions on Knowledge Discovery from Data (TKDD). 2015. Vol. 10 (1). P. 5. https://doi.org/10.1145/2733381Vardi Y., Zhang C.-H. A modified Weiszfeld algorithm for the Fermat–Weber location problem // Mathematical Programming. 2001. Vol. 90. Р. 559–566. https://doi.org/10.1007/PL00011435Vardi Y., Zhang C.-H. A modified Weiszfeld algorithm for the Fermat–Weber location problem // Mathematical Programming. 2001. Vol. 90. Р. 559–566. https://doi.org/10.1007/PL00011435Reimers N., Gurevych I. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks // Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019. Р. 3982–3992. Hong Kong, China: Association for Computational Linguistics. https://doi.org/10.18653/v1/D19-1410Reimers N., Gurevych I. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks // Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019. Р. 3982–3992. Hong Kong, China: Association for Computational Linguistics. https://doi.org/10.18653/v1/D19-1410Hugging Face. XLM-RoBERTa (large): specs (24 layers, ~550M params). 2020–2024. URL: https://huggingface.co/transformers/v3.4.0/pretrained_models.htmlHugging Face. XLM-RoBERTa (large): specs (24 layers, ~550M params). 2020–2024. URL: https://huggingface.co/transformers/v3.4.0/pretrained_models.htmlCôté M.-A. et al. TextWorld: A Learning Environment for Text-Based Games // Computer Games (CGW@IJCAI 2018). 2019. Vol. 1017 (CCIS). Р. 41–75. https://doi.org/10.1007/978-3-030-24337-1_3Côté M.-A. et al. TextWorld: A Learning Environment for Text-Based Games // Computer Games (CGW@IJCAI 2018). 2019. Vol. 1017 (CCIS). Р. 41–75. https://doi.org/10.1007/978-3-030-24337-1_3Russell S., Norvig P. Artificial Intelligence: A Modern Approach. 4th ed. Pearson, 2020. Chapter 11: Planning and Acting.Russell S., Norvig P. Artificial Intelligence: A Modern Approach. 4th ed. Pearson, 2020. Chapter 11: Planning and Acting.Schmidhuber J. Gödel Machines: Self-Referential Universal Problem Solvers Making Provably Optimal Self-Improvements // Artificial General Intelligence. 2007. Р. 199–226. https://doi.org/10.1007/978-3-540-68677-4_7Schmidhuber J. Gödel Machines: Self-Referential Universal Problem Solvers Making Provably Optimal Self-Improvements // Artificial General Intelligence. 2007. Р. 199–226. https://doi.org/10.1007/978-3-540-68677-4_7Yin X. et al. Gödel Agent: A Self-Referential Agent Framework for Recursively Self-Improvement // Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL 2025). 2025. Р. 27890–27913. https://aclanthology.org/2025.acl-long.1354/Yin X. et al. Gödel Agent: A Self-Referential Agent Framework for Recursively Self-Improvement // Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL 2025). 2025. Р. 27890–27913. https://aclanthology.org/2025.acl-long.1354/Ataeva O.M., Serebryakov V.A. Ontology of the Digital Semantic Library LibMeta // Informatics and Its Applications. 2018. Vol. 12, No. 1. P. 2–10 (In Russian).Ataeva O.M., Serebryakov V.A. Ontology of the Digital Semantic Library LibMeta // Informatics and Its Applications. 2018. Vol. 12, No. 1. P. 2–10 (In Russian).

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