SEMANTIC MATCHING METHODS AND THEIR APPLICATION IN INTELLIGENT INFORMATION SYSTEMS

Authors

  • Boboqulov J.J., Sharipova D.J., Saidrasulov Sh.N. Tashkent University of Information Technologies named after Muhammad al-Khwarizmi, Tashkent, Uzbekistan Author

Keywords:

semantic matching, semantic similarity, embedding, dense retrieval, BERT, Sentence-BERT, ontology, knowledge graph, intelligent information systems, retrieval-augmented generation, approximate nearest neighbour search, low-resource languages.

Abstract

This article examines semantic matching — the estimation of correspondence between textual objects by meaning rather than by surface lexical form — which has become the computational core of modern intelligent information systems. Four generations of methods are distinguished and analysed: lexical and statistical methods (TF-IDF, BM25, LSA), knowledge-based ontological methods (WordNet, knowledge graphs), distributional word vectors (Word2Vec, GloVe, FastText) and contextual neural models (BERT, Sentence-BERT, dense retrievers). For each generation the mathematical basis, the computational cost and the limits of applicability are stated. The cross-encoder, bi-encoder and late-interaction architectures are compared on accuracy, query latency and index size, and a six-stage reference model of retrieval is constructed in which the cost of each successive stage rises while the number of documents it examines falls. Approximate nearest-neighbour indexing and hybrid sparse–dense fusion are described, evaluation corpora and ranking metrics are systematised, and the application of the methods to semantic search, retrieval-augmented generation, recommendation, classification and data integration is set out. A separate section addresses the morphologically rich and low-resource case of the Uzbek language.

References

1.Salton G., Wong A., Yang C.S. A Vector Space Model for Automatic Indexing // Communications of the ACM. – 1975. – Vol. 18, No. 11. – P. 613–620.

2.Furnas G.W., Landauer T.K., Gomez L.M., Dumais S.T. The vocabulary problem in human-system communication // Communications of the ACM. – 1987. – Vol. 30, No. 11. – P. 964–971.

3.Robertson S., Zaragoza H. The Probabilistic Relevance Framework: BM25 and Beyond // Foundations and Trends in Information Retrieval. – 2009. – Vol. 3, No. 4. – P. 333–389.

4.Deerwester S., Dumais S.T., Furnas G.W. et al. Indexing by Latent Semantic Analysis // Journal of the American Society for Information Science. – 1990. – Vol. 41, No. 6. – P. 391–407.

5.Blei D.M., Ng A.Y., Jordan M.I. Latent Dirichlet Allocation // Journal of Machine Learning Research. – 2003. – Vol. 3. – P. 993–1022.

6.Miller G.A. WordNet: A Lexical Database for English // Communications of the ACM. – 1995. – Vol. 38, No. 11. – P. 39–41.

7.Wu Z., Palmer M. Verb Semantics and Lexical Selection // Proceedings of the 32nd Annual Meeting of the ACL. – 1994. – P. 133–138.

8.Resnik P. Using Information Content to Evaluate Semantic Similarity in a Taxonomy // Proceedings of IJCAI. – 1995. – P. 448–453.

9.Lin D. An Information-Theoretic Definition of Similarity // Proceedings of ICML. – 1998. – P. 296–304.

10.Euzenat J., Shvaiko P. Ontology Matching. 2nd ed. – Berlin: Springer, 2013. – 511 p.

11.Bordes A., Usunier N., Garcia-Durán A. et al. Translating Embeddings for Modeling Multi-relational Data // Advances in NeurIPS. – 2013. – P. 2787–2795.

12.Mikolov T., Chen K., Corrado G., Dean J. Efficient Estimation of Word Representations in Vector Space // arXiv:1301.3781. – 2013.

13.Pennington J., Socher R., Manning C. GloVe: Global Vectors for Word Representation // Proceedings of EMNLP. – 2014. – P. 1532–1543.

14.Bojanowski P., Grave E., Joulin A., Mikolov T. Enriching Word Vectors with Subword Information // Transactions of the ACL. – 2017. – Vol. 5. – P. 135–146.

15.Kusner M., Sun Y., Kolkin N., Weinberger K. From Word Embeddings to Document Distances // Proceedings of ICML. – 2015. – P. 957–966.

16.Vaswani A., Shazeer N., Parmar N. et al. Attention Is All You Need // Advances in NeurIPS. – 2017. – P. 5998–6008.

17.Devlin J., Chang M.-W., Lee K., Toutanova K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding // Proceedings of NAACL-HLT. – 2019. – P. 4171–4186.

18.Reimers N., Gurevych I. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks // Proceedings of EMNLP-IJCNLP. – 2019. – P. 3982–3992.

19.Karpukhin V., Oğuz B., Min S. et al. Dense Passage Retrieval for Open-Domain Question Answering // Proceedings of EMNLP. – 2020. – P. 6769–6781.

20.Khattab O., Zaharia M. ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT // Proceedings of SIGIR. – 2020. – P. 39–48.

21.Gao T., Yao X., Chen D. SimCSE: Simple Contrastive Learning of Sentence Embeddings // Proceedings of EMNLP. – 2021. – P. 6894–6910.

22.Malkov Yu.A., Yashunin D.A. Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs // IEEE Transactions on Pattern Analysis and Machine Intelligence. – 2020. – Vol. 42, No. 4. – P. 824–836.

23.Johnson J., Douze M., Jégou H. Billion-Scale Similarity Search with GPUs // IEEE Transactions on Big Data. – 2021. – Vol. 7, No. 3. – P. 535–547.

24.Thakur N., Reimers N., Rücklé A. et al. BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models // NeurIPS Datasets and Benchmarks Track. – 2021.

25.Muennighoff N., Tazi N., Magne L., Reimers N. MTEB: Massive Text Embedding Benchmark // Proceedings of EACL. – 2023. – P. 2014–2037.

26.Lewis P., Perez E., Piktus A. et al. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks // Advances in NeurIPS. – 2020. – P. 9459–9474.

27.Feng F., Yang Y., Cer D. et al. Language-agnostic BERT Sentence Embedding // Proceedings of ACL. – 2022. – P. 878–891.

28.Chen J., Xiao S., Zhang P. et al. BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings // arXiv:2402.03216. – 2024.

29.Conneau A., Khandelwal K., Goyal N. et al. Unsupervised Cross-lingual Representation Learning at Scale // Proceedings of ACL. – 2020. – P. 8440–8451.

30.MTEB Multilingual v2 leaderboard results. – URL: https://www.llmreference.com/benchmark/mteb-multilingual-v2 (accessed 4 November 2026).

31.Reading the MTEB score for retrieval workloads. – URL: https://techsy.io/en/blog/mteb-score-explained-rag (accessed 4 November 2026).

32.Comparative analysis of embedding models, 2026. – URL: https://futureagi.com/blogs/best-embedding-models-2025 (accessed 4 November 2026).

33.Leading and domain-specific models on the MTEB leaderboard. – URL: https://modal.com/blog/mteb-leaderboard-article (accessed 4 November 2026).

Downloads

Published

2026-11-06