N.A. Borsuk1, T.A. Onufrieva2, L.V. Tsarev3, P.A. Deryugin4, A.Yu. Titov5

1–5 Kaluga Branch of Bauman Moscow State Technical University (Kaluga, Russia)

1 borsuk.65@yandex.ru, 2 onufrievata@mail.ru, 3 x174101@gmail.com,

4 shadowmadness792@mail.ru, 5 alexcandr40@mail.ru

Problem setting. Nowadays, computer technologies are used more and more in communication between people, for example, messengers on various devices. However, in the process of communicating or sending large amounts of textual information, people often make grammatical mistakes. And in business communication, this is categorically unacceptable. Therefore, the question arises of developing a semantic analyzer for the Russian-speaking audience.

Target. Improving the literacy of the Russian-speaking population by developing a semantic analyzer that works with a large amount of text data.

Results. The approbation of the developed semantic analyzer was carried out on large amounts of data and showed 68.7% correctness of the correction of words in sentences.

Practical significance. The possibility of developing a semantic analyzer using neural networks is shown. The network will continue to be trained on big Data Set in the future.

Borsuk N.A., Onufrieva T.A., Tsarev L.V., Deryugin P.A., Titov A.Yu. Development of a semantic analyzer using neural networks. Neurocomputers. 2024. V. 26. № 1. Р. 5-13. DOI: https://doi.org/10.18127/j19998554-202401-01 (In Russian)

1. Yarushkina N.G., Mashkin V.S., Filippov A.A., Guskov G.Yu., Romanov A.A., Namestnikov A.M. Development of a software system for semantic analysis of social media content. Radio Engineering. 2018. №. 6. P. 73–79. (In Russian)
2. Novikov A.Yu., Stolyarov M.G. Algorithm of primary semantic interpretation of clauses in the interests of building a subsystem of primary semantic analysis in the system of automatic processing of textual information. High-tech technologies. 2011. V. 12. № 8.
   P. 54–59. (In Russian)
3. Dikovitsky V.V. Semantic text analysis using neural network analysis of morphology and syntax. Proceedings of the Kola Scientific Center of the Russian Academy of Sciences. 2017. V. 8. № 3-8. P. 109–115. (In Russian)
4. Internet and social media statistics for 2023 – figures and trends in the world and in Russia. [Electronic resource] – Access mode: https://www.web-canape.ru/business/statistika-interneta-i-socsetej-na-2023-god-cifry-i-trendy-v-mire-i-v-rossii/, date of reference 10.18.2023.
5. Pashchenko A.V. Technologies of image recognition and syntactic analysis on the Russian market. Bulletin of the Taganrog Institute of Management and Economics. 2022. № 1(35). P. 116–118. (In Russian)
6. Soroka B.O., Kubanskikh O.V. The main problems in the creation of semantic-syntactic analyzers. Scientific notes of the Bryansk State University. 2017. № 2(6). P. 21–24. (In Russian)
7. Traulko M.V. Software implementation of fuzzy search for textual information in a dictionary using the Leven-Stein distance. Forum of Young Scientists. 2017. № 12(16). P. 1827–1832. (In Russian)
8. Postolit A.V. Fundamentals of artificial intelligence in Python examples. St. Petersburg: BHV-Petersburg. 2021. 448 p. (In Russian)
9. Rashka S., Mirjalili V. Python and machine learning. Ed. 3-rd. M.: DMK Press. 2021. 848 p. (In Russian)
10. Lonza A. Reinforcement learning algorithms in Python. M.: DMK Press. 2020. 286 p. (In Russian)
11. Weidman S. Deep learning: easy development of projects in Python. St. Petersburg: Peter. 2021. 272 p. (In Russian)
12. Elbon K. Machine learning using Python. Collection of recipes. St. Petersburg: BHV-Petersburg. 2019. 384 p. (In Russian)
13. Grus J. Data Science. Data science from scratch. St. Petersburg: BHV-Petersburg. 2020. 416 p. (In Russian)