Semantic Search of Text Documents
DOI:
https://doi.org/10.15407/intechsys.2026.04.068Keywords:
semantic search, embedding models, sentence embedding, system architecture, searching efectivnessAbstract
Search systems are essential part of computer systems usage, and in particular for information retrival and usage. To address the problem of efectivness of information retrival semantic search systems can be used, as they provide deep searching capabilities due to usage of neural models for perception of text semantic and meaning. xis enables a more comprehensive relevancy of search results comparing to classical lexical search methods. xis paper address problem of designing a semantic search system that can be used for search in local documents collection. For achieving this goal an architecture with usage of vector database (ChromaDB), neural model execution service (Ollama) and asyncronous task queue service (Celery) is proposed. xe developed system provides precision and recall of 56.67% and 94.44% corespondingly, which is on the level with analogs. Also for determing the best in terms of search relevance neural model such models were compared: Doc2Vec, BERT and EmbeddingGemma.
References
Mohammed H.K., Indrani B. Secure Semantic Retrieval over Encrypted Cloud Data: A Dual-Index System with Lightweight Fuzzy Encryption and BERT-Based Semantic Indexing. Diyala Journal of Engineering Sciences, 2026, Vol.19 (1), 160–180. https://doi.org/10.24237/djes.2026.19112
Nodehi A.K., Charkari N.M. A metaheuristic with a neural surrogate function for Word Sense Disambiguation. Machine Learning with Applications, 2022, Vol. 9, Article 100369. https://doi.org/10.1016/j.mlwa.2022.100369
Arteaga C., Ray U., Park J., Paz A. Semantic search approach for information extraction from traffic crash narratives. Transportation Research Interdisciplinary Perspectives, 2026, Vol. 36, Article 101888. https://doi.org/10.1016/j.trip.2026.101888
Mageshwari V., Shrijith J. Linguistic-Neural Hybrid Architectures for Semantic Search: Optimizing Recall with POS Filtering and Query Expansion. IEEE Access, 2026, Vol. 14, 28564–28572. https://doi.org/10.1109/access.2026.3663716
Daffa M.R., Yaqin M.A. Implementation of Semantic Similarity for Book Search in Digital Library. Electrics, Electronics, Communications, Controls, Informatics, Systems, 2025, Vol. 19 (3), 190–196. https://doi.org/10.21776/jeeccis.v19i3.1796
Abimbola J.O., Kuaban G.S., Ajayi S.A. Open-Source Embedding Models: A Comprehensive Survey of Techniques, Benchmarks, and Applications. IEEE Access, 2026, Vol. 14, 41284–41302. https://doi.org/10.1109/access.2026.3670100
Nazir S., Asif M., Sahi S. A., Ahmad S., Ghadi Ya.Ya., Aziz M.H. Toward the Development of Large-Scale Word Embedding for Low-Resourced Language. EEE Access, 2022, Vol. 10, 54091–54097. https://doi.org/10.1109/access.2022.3173259
Blagec, K., Xu, H., Agibetov, A. et al. Neural sentence embedding models for semantic similarity estimation in the biomedical domain. BMC Bioinformatics, 2019, Vol. 20, Article 178. https://doi.org/10.1186/s12859-019-2789-2
Guesmi M., Chatti M.A., Kadhim L., Joarder S., Ain Q.Ul. Semantic Interest Modeling and Content-Based Scientific Publication Recommendation Using Word Embeddings and Sentence Encoders. Multimodal Technologies and Interaction, 2023, Vol. 7 (9), Article 91. https://doi.org/10.3390/mti7090091
Dolci T., Azzalini F., Tanelli M. Improving Gender-Related Fairness in Sentence Encoders: A Semantics-Based Approach. Data Science and Engineering, 2023, Vol. 8, 177–195. https://doi.org/10.1007/s41019-023-00211-0
What is Doc2Vec? educative.io. URL: https://www.educative.io/answers/what-is-doc2vec [Accessed 23 Jan.2026]
What Is the BERT Model and How Does It Work? Coursera. URL: https://www.coursera.org/articles/bert-model [Accessed 23 Jan.2026]
EmbeddingGemma model overview. Google AI for Developers. URL: https://ai.google.dev/gemma/docs/embeddinggemma [Accessed 23 Jan.2026]
Vera H.S. et al. EmbeddingGemma: Powerful and Lightweight Text Representations. ArXiv, 2509.20354. https://doi.org/10.48550/arXiv.2509.20354
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Copyright Holder is the publisher of the Paper (The Institute of Information Technologies and Systems of the NAS of Ukraine), and/or the publisher of the Paper (PH "Akademperiodika" of the NAS of Ukraine), to that the The Institute of Information Technologies and Systems of the NAS of Ukraine on the basis of a sublicense publishing agreement granted the right to publish the work and the right to indicate the publisher after the copyright sign.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
The paper is an Open Access under the CC BY-NC-ND 4.0 license - Attribution-NonCommercial-NoDerivatives 4.0 International.
