• A
  • A
  • A
  • АБВ
  • АБВ
  • АБВ
  • A
  • A
  • A
  • A
  • A
Обычная версия сайта
  • RU
  • EN
  • HSE University
  • Publications
  • Book chapter
  • A Comparison of Neural Networks Architectures for Diacritics Restoration
  • RU
  • EN
Расширенный поиск
Высшая школа экономики
Национальный исследовательский университет
Priority areas
  • business informatics
  • economics
  • engineering science
  • humanitarian
  • IT and mathematics
  • law
  • management
  • mathematics
  • sociology
  • state and public administration
by year
  • 2027
  • 2026
  • 2025
  • 2024
  • 2023
  • 2022
  • 2021
  • 2020
  • 2019
  • 2018
  • 2017
  • 2016
  • 2015
  • 2014
  • 2013
  • 2012
  • 2011
  • 2010
  • 2009
  • 2008
  • 2007
  • 2006
  • 2005
  • 2004
  • 2003
  • 2002
  • 2001
  • 2000
  • 1999
  • 1998
  • 1997
  • 1996
  • 1995
  • 1994
  • 1993
  • 1992
  • 1991
  • 1990
  • 1989
  • 1988
  • 1987
  • 1986
  • 1985
  • 1984
  • 1983
  • 1982
  • 1981
  • 1980
  • 1979
  • 1978
  • 1977
  • 1976
  • 1975
  • 1974
  • 1973
  • 1972
  • 1971
  • 1970
  • 1969
  • 1968
  • 1967
  • 1966
  • 1965
  • 1964
  • 1963
  • 1958
  • More
Subject
News
April 28, 2026
Scientists Develop Algorithm for Accurate Financial Time Series Forecasting
Researchers at the HSE Faculty of Computer Science benchmarked more than 200,000 model configurations for predicting financial asset prices and realised volatility, showing that performance can be improved by filtering out noise at specific frequencies in advance. This technique increased accuracy in 65% of cases. The authors also developed their own algorithm, which achieves accuracy comparable to that of the best models while requiring less computational power. The study has been published in Applied Soft Computing.
April 27, 2026
Fair Division: How Mathematics Helps to Divide the Indivisible
How can items be allocated among participants so that no one feels short-changed? Alexander Karpov, Assistant Professor at the Faculty of Economic Sciences, and his Singaporean colleague, Prof. Warut Suksompong, set out to find a mathematical answer to this question. In this interview, they discuss how a model of rational preferences is constructed, why one cannot rely on a simple sum of values, and where an algorithm that asks a minimal number of questions can be useful.
April 24, 2026
Electronics of the Future: Why Superconductors and Spintronics Work Together
It was once believed that superconductivity and magnetism avoided each other like the devil avoids holy water. However, modern nanostructures prove the opposite. A Russian theoretical physicist and Indian experimentalists have joined forces to create the electronics of the future—free from energy losses. Nataliya Pugach, Professor at the School of Electronic Engineering at HSE MIEM and Leading Research Fellow at the Quantum Nanoelectronics Laboratory, explains how a long-standing acquaintance in Cambridge grew into a mirror laboratory project with the Indian Institute of Technology Bombay (IIT Bombay), how superconducting spintronics works, and what surprises a researcher in India beyond the university campus.

 

Have you spotted a typo?
Highlight it, click Ctrl+Enter and send us a message. Thank you for your help!

Publications
  • Books
  • Articles
  • Chapters of books
  • Working papers
  • Report a publication
  • Research at HSE

?

A Comparison of Neural Networks Architectures for Diacritics Restoration

P. 242–253.
Klyshinskiy E., Карпик О. В., Бондаренко А. В.

Neural networks are widely used for the task of diacritics restoration last years. Authors use different architectures of neural network for selected languages. In this paper, we demonstrated that an architecture should be selected according to a language in hand. It also depends on a task one states: low and full resourced languages could use different architectures. We demonstrated that common used accuracy metric should be changed in this task to precision and recall due to the heavy unbalanced nature of the input data. The paper contains results for seven languages: Croatian, Slovak, Romanian, French, German, Latvian, and Turkish.

Language: English
Full text
DOI
Text on another site
Keywords: neural networksdiacritics restorationout-of-vocabulary words

In book

Recent Trends in Analysis of Images, Social Networks and Texts. 9th International Conference, AIST 2020, Skolkovo, Moscow, Russia, October 15–16, 2020 Revised Supplementary Proceedings
Vol. 12602. , Springer, 2021.
Similar publications
Screen-Cam Imitation Module for Improving Data Hiding Robustness
Dzhanashia K., Aleksandr Fedosov, Oleg Evsutin, Sensors 2025 Vol. 25 No. 23 Article 7726
Using an attack-simulation module is a well-recognized approach to improving the robustness of end-to-end neural-network-based data-hiding schemes. However, most proposed attack simulators are limited in the types of attacks they cover, usually handling only a basic set of digital transformations. Real, in-demand use cases for data-hiding methods may involve modifications that cannot be modeled by ...
Added: November 28, 2025
Understanding the training dynamics of CoLaNET by its simplified model
O.A. Goryunov, Maslennikov O. V., Kiselev M. V. et al., Chaos, Solitons and Fractals 2026 Vol. 203 Article 117663
Training complex, biologically plausible Spiking Neural Networks (SNNs) with local learning rules is a significant challenge for theoretical analysis. Here we address this problem by developing a comprehensive analytical theory for the learning dynamics of CoLaNET, a recently proposed columnar SNN. In particular, we consider a simplified model that captures the core algorithmic logic of ...
Added: November 28, 2025
Смежные права на результаты интеллектуальной деятельности, созданные искусственным интеллектом: философско-правовой анализ замены критерия творчества на критерий инвестиций
Pakshin P., Актуальные проблемы российского права 2025 Т. 20 № 11 С. 11–18
The paper substantiates the necessity of providing legal protection for the results of intellectual works created by artificial intelligence through the mechanism of related rights. It examines ways to reduce legal risks associated with the creation of intellectual property using artificial intelligence technologies and offers a philosophical and legal analysis of the proposed hypothesis, namely, ...
Added: November 27, 2025
2025 International Joint Conference on Neural Networks (IJCNN)
IEEE, 2025.
Added: November 15, 2025
Segmentation of Vertebral Arteries on the MR Images
Prikhodko R., Moshkin A., Romanov A., , in: 2025 International Russian Automation Conference (RusAutoCon).: IEEE, 2025. P. 273–278.
The vertebral arteries are one of the most important sources of blood supply to the brain, therefore any pathological changes in them can be the reason behind serious diseases. Magnetic Resonance Imaging (MRI) allows diagnosticians to examine main arteries, which is exceptionally important for effective diagnosis. However, because of the small size of arteries relative ...
Added: November 6, 2025
Машинное обучение и представление информации: новые возможности цифровых архивов (рецензия на книгу: Artificial Intelligence, Archives and Manuscripts. New Relationships between the Virtual Archive and Its Referent. Edinburgh: University of Edinburgh, 2025
Penskaja E., Имагология и компаративистика 2025 № 23 С. 380–389
The book Artificial Intelligence, Archives and Manuscripts. New Relationships between the Virtual Archive and Its Referent (2025) is presented. This collective monograph discusses both technological and legal, intellectual issues that researchers and archivists face in automated work with manuscript heritage, artificial intelligence and neural networks. ...
Added: October 30, 2025
Free energy of neural network can predict accuracy after pruning
Surkov A., Sergei Koltcov, Ignatenko V. et al., Physica A: Statistical Mechanics and its Applications 2025 Vol. 681 Article 131085
Neural networks are powerful tools capable of achieving state-of-the-art performance across a wide range of tasks; however, their effectiveness often comes at the cost of extremely large numbers of parameters, which can hinder their deployment in resource-constrained environments. To address this issue, various pruning techniques have been proposed to reduce model size and complexity while ...
Added: October 30, 2025
Artificial Neural Networks and Machine Learning. ICANN 2025 International Workshops and Special Sessions: 34th International Conference on Artificial Neural Networks, Kaunas, Lithuania, September 9–12, 2025, Proceedings, Part V
Cham: Springer, 2025.
This book constitutes the refereed proceedings of 34th International Workshops which were held in conjunction with the 34th International Conference on Artificial Neural Networks and Machine Learning, ICANN 2025, held in Kaunas, Lithuania, September 9–12, 2025.   The 20 full papers and 8 abstracts included in this workshop volume were carefully reviewed and selected from 42 submissions. ...
Added: September 29, 2025
Цифровой театр абсурда: могут ли нейросети поставить новую научную проблему перед психологией? Кейс-сравнение ChatGPT и DeepSeek
Хашутогова У. П., Berezner T., Poddiakov A., Новые психологические исследования 2025 № 3 С. 100–125
The rapid advancement of artificial intelligence technologies has drawn increasing attention from psychological researchers. While neural networks are being integrated into nearly all domains of human activity, the boundaries of their applicability remain unclear — particularly regarding the originality and practical value of the content they generate. Proponents advocate for their widespread adoption, whereas skeptics ...
Added: September 4, 2025
Этические аспекты использования искусственного интеллекта в образовании при подготовке обучающимися письменных работ
Поставнева И. В., Dvoinin A., Информация и образование: границы коммуникаций 2025 Т. 25 № 17 С. 58–59
The article discusses ethically correct and incorrect ways of using generative artificial intelligence by students when preparing written works. In this context, the boundaries of ethically acceptable actions with neural networks are outlined. ...
Added: August 19, 2025
Распознавание рукописного текста и интеллектуальный анализ: возможности нейронных технологий (на примере работы с «Дневником» Ф.П. Литке)
Boltunova E., Laptev A., Имагология и компаративистика 2025 № 23 С. 358–379
Added: June 16, 2025
Neuro- vs brain-: диалог искусственного интеллекта и мозга в пространстве нейроарта
Mcvey A. V., Коммуникации. Медиа. Дизайн 2025 Т. 10 № 1 С. 74–112
В статье многосторонне исследуется понятие «нейроарт». Проведен анализ существующих в художественном и медиадискурсах трактовок данного понятия, выявлена двойственная практика его употребления в отношении двух различных направлений современного искусства: 1) художественных практик, связанных с использованием искусственных нейронных сетей, 2) художественных практик, использующих нейротехнологии в качестве выразительных средств. Каждое из направлений проанализировано с учетом своей медиальной специфичности. ...
Added: May 5, 2025
Особенности правового режима интеллектуальной собственности объектов, созданных искусственным интеллектом в медицине
Лебедева Д. А., Труды по интеллектуальной собственности 2025 Т. 53 № 2 С. 111–119
In the modern world, artificial intelligence (AI) technologies are being actively introduced into various fields of activity, including medicine. This makes it possible to automate complex processes, increase their accuracy and efficiency, and opens up new opportunities for the diagnosis, treatment, and prevention of diseases. However, with the development of AI, there is a need ...
Added: April 10, 2025
Forecasting market volatility using AI and ML models
Pshichenko D., Znanstvena misel 2024 No. 96 P. 38–42
The article analyzes the application of artificial intelligence (AI) models for forecasting market volatility (MV). Examples of algorithms such as recurrent neural networks (RNN), long short-term memory (LSTM) networks, and regression methods are studied, demonstrating their effectiveness in processing time series and identifying complex data patterns. The importance of integrating machine learning (ML), as a ...
Added: March 10, 2025
Study of artificial intelligence models for big data analysis in project management
Pshichenko D., International Journal of Humanities and Natural Sciences 2024 Vol. 8-3(95) P. 180–185
This study explores the application of artificial intelligence (AI) and machine learning (ML) models for big data analysis in project management. By leveraging specific ML algorithms such as decision trees, random forests, support vector machines, neural networks, kmeans clustering, gradient boosting, and natural language processing, project management practices are significantly enhanced. These technologies improve decision-making, ...
Added: March 10, 2025
Роль искусственного интеллекта в управлении кризисными ситуациями в экономике
Pshichenko D., Тенденции развития науки и образования 2024 № 112(3) С. 117–122
The article examines the role of artificial intelligence (AI) in managing crisis situations in the economy. Various AI technologies for forecasting economic shocks and minimizing their consequences are analyzed. Examples of successful AI applications in various sectors are studied. It is emphasized that the use of AI significantly enhances the resilience and adaptability of economic ...
Added: March 10, 2025
Complex landscape of the cost function in a simple machine learning regression task
Soloviev I., Klinshov V., European Physical Journal: Special Topics 2024 P. 1–8
We carry out detailed study of the phase space of a small neural network in a paradigmatic machine learning regression problem. In spite of its simplicity, the system phase space turns to be extremely complex with a plenty of local minima of the cost function. These minima differ in depth by several orders of magnitude, ...
Added: February 20, 2025
Интеллектуальные информационные системы: теория и практика. Сборник научных статей по материалам V Международной конференции (Курск, 19–21 ноября 2024 года)
Курск: Курский государственный университет, 2024.
The collection publishes scientific articles based on the materials of the V International Scientific and Technical Conference "Intelligent Information Systems: Theory and Practice". The publication is addressed to students, postgraduates, university professors, candidates and doctors of science, practicing specialists, and anyone interested in the design and development of intelligent information systems, their practical applications, as ...
Added: February 17, 2025
Традиционные духовно-нравственные ценности и права человека в эпоху цифровизации и искусственного интеллекта
Овчинников А. И., Дмитриева О. В., Конопий А. С. et al., Вестник юридического факультета Южного федерального университета 2024 Т. 11 № 1 С. 137–147
The article is focused on the main results of the scientific and theoretical conference held on February 28 on the theme “Traditional spiritual and moral values and human rights in the era of digitalization and artificial intelligence”. As the most important problem, the organizers and participants of the event chose a scientific and theoretical understanding of human rights ...
Added: January 19, 2025
The Use Of Artificial Intelligence And Other Technologies In Criminal Proceedings: Problems, Solutions And Prospects
Rastoropov S., Solomatina A., Yakovleva V. et al., Relacoes Internacionais no Mundo Atual 2024 Vol. 3 No. 45 P. 381–391
This article aims to form an idea of the developed new technologies and, based on the analysis of their practical potential, to determine the possibility of using them in the investigation of crimes, especially those committed in the field of information and telecommunication technologies. ...
Added: December 5, 2024
Bridging Gaps in Russian Language Processing: AI and Everyday Conversations
Tatiana Sherstinova, Nikolay Mikhaylovskiy, Evgenia Kolpashchikova et al., , in: Proceedings of the 35th Conference of Open Innovations Association FRUCT, 24-26 April 2024, Tampere, FinlandIssue 1.: FRUCT Oy, 2024. P. 253–258.
Contemporary advancements in NLP and neural network techniques are paving the way to enhance and harness traditional linguistic resources and corpora, as well as expand the methods of applying neural networks for complex language material. Thus, a weak point for both theoretical and applied linguistic tasks is the processing of spontaneous everyday speech. Two experiments ...
Added: November 29, 2024
Development of a Detector for Stamps on Images
Kseniia Prokudina, Mikhail Skriplyonok, Alexander Vostrikov, , in: 2024 International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM), 20-24 May 2024.: IEEE, 2024. P. 865–869.
Added: November 26, 2024
  • About
  • About
  • Key Figures & Facts
  • Sustainability at HSE University
  • Faculties & Departments
  • International Partnerships
  • Faculty & Staff
  • HSE Buildings
  • HSE University for Persons with Disabilities
  • Public Enquiries
  • Studies
  • Admissions
  • Programme Catalogue
  • Undergraduate
  • Graduate
  • Exchange Programmes
  • Summer University
  • Summer Schools
  • Semester in Moscow
  • Business Internship
  • Research
  • International Laboratories
  • Research Centres
  • Research Projects
  • Monitoring Studies
  • Conferences & Seminars
  • Academic Jobs
  • Yasin (April) International Academic Conference on Economic and Social Development
  • Media & Resources
  • Publications by staff
  • HSE Journals
  • Publishing House
  • iq.hse.ru: commentary by HSE experts
  • Library
  • Economic & Social Data Archive
  • Video
  • HSE Repository of Socio-Economic Information
  • HSE1993–2026
  • Contacts
  • Copyright
  • Privacy Policy
  • Site Map
Edit