• A
  • A
  • A
  • АБВ
  • АБВ
  • АБВ
  • A
  • A
  • A
  • A
  • A
Обычная версия сайта
  • RU
  • EN
  • HSE University
  • Publications
  • Articles
  • Языковые модели для предобработки текстов в машинном переводе
  • 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
  • 2028
  • 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
October 5, 2026
‘The Climate Transition Is Not Necessarily a Limitation for Business
Linara Khadimullina works in the field of low-carbon development. In an interview with the Young Scientists of HSE project, she spoke about why nature is not just a beautiful backdrop, her research on the role of sustainable corporate governance in reducing greenhouse gas emissions, and growing plants as a source of inspiration.
October 5, 2026
Africa, Youth, and Civic Dialogue: Public Diplomacy Discussed at HSE University
In late September, HSE University hosted a roundtable discussion titled Civil Society in African Countries and Youth Participation in Public Diplomacy. Representatives of non-governmental organisations from Ghana, Ethiopia, and Russia, along with students from HSE University’s Bachelor’s Programme in Public Administration, discussed how young people without official diplomatic status can influence relations between countries and how the nonprofit sector can remain sustainable amid declining grant funding.
October 1, 2026
HSE Researchers Show How Congenital Motor Disorders Affect Brain Development
Researchers from HSE University’s Institute for Cognitive Neuroscience have synthesised the findings of their previous studies on brain development in children with obstetric brachial plexus palsy and arthrogryposis. Their analysis shows that impaired motor function in early childhood not only limits children’s motor experience but also affects memory, categorical thinking, and information processing. The study has been published in Frontiers in Psychology.

 

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

?

Языковые модели для предобработки текстов в машинном переводе

Научно-техническая информация. Серия 2: Информационные процессы и системы. 2025. № 7. С. 32–44.
Mylnikova A., Mylnikov L.
Research target: Computer Science
Language: Russian
DOI
Keywords: NLPкорпус текстовсинтаксическая разметкамашинный переводклассификация предложений по цели высказыванияязыковая модельчастеречная разметкаBERTскелетная структура текстаLLM
Similar publications
On Practical Aspects of Constructing Quasi-Cyclic Subfield Subcodes of Dual Elliptic Codes and Their Application in McEliece-type Cryptosystems
Kuninets A., IEEE Transactions on Information Theory 2026 P. 1–1
In this work we study the applicability of Quasi-Cyclic Subfield Subcodes of Dual Elliptic (QC-SSDE) codes for integration into code-based cryptographic schemes. Detailed algorithms are provided for constructing parity-check matrices as well as block-circulant parity-check matrices for this family of codes, accompanied by empirical results that enable the construction of QC-SSDE codes with predetermined dimensions. ...
Added: October 3, 2026
Инкрементальный метод обновления многомерного куба по неупорядоченному потоку событий журналов информационных систем
Zykov S. V., Уфимцев Г. А., Моделирование, оптимизация и информационные технологии 2026 Т. 14 № 8 С. 1–13
Информационные системы формируют большие объёмы событийных журналов, которые используются для анализа работы приложений и сервисов. При этом события могут поступать в аналитический контур позже момента их фактического возникновения и не в исходном порядке. Такая рассинхронизация приводит к ошибкам при построении агрегированных временных показателей, а регулярный полный пересчёт многомерного аналитического куба требует значительных вычислительных затрат. Целью ...
Added: October 2, 2026
Polarization of opinions in the group: a modeling algorithm considering the dynamics of social bonds
Chebotarev V., Andreyuk D., Elizarova Anastasiya et al., Procedia Computer Science 2022 Vol. 213 No. C P. 596–601
The dynamics of opinion in a group are of interest for a number of practical purposes. In particular, consensus helps and polarization of opinions hinders cohesive teamwork. Existing approaches for modeling opinion dynamics mostly do not take into account the dynamism of social relations in a group. This paper proposes an algorithm and a program ...
Added: October 2, 2026
Enhancing Boundary Stability in Decision Trees and Random Forests: A Weighted Sample Duplication Approach
Konstantinov A., Elizarova Anastasiya P., Utkin L., Computing, Telecommunications and Control 2026 Vol. 19 No. 1 P. 16–25
Decision trees and their ensemble extensions, such as random forests, are widely used as classification models due to their simplicity and interpretability. However, in many real-world tasks where class labels overlap in the feature space, standard decision trees rely on hard splits that create fragile decision boundaries. In these regions, small perturbations in the input ...
Added: October 2, 2026
Bayesian Adaptive Sparse Copula
Prokhorov A., Burda M., Journal of Computational and Graphical Statistics 2026 P. 1–13
Bayesian nonparametric density estimation procedures are typically based on single-scale priors, such as Dirichlet process mixtures. Alternative multiscale density priors built on decision trees have many well-known advantages, including the ability to characterize abrupt local changes and to provide an estimate with a desired level of resolution. Despite their theoretical appeal, multiscale methods have typically ...
Added: October 2, 2026
Pericyte-derived cancer-associated fibroblasts correlate with poor survival and are enriched after chemoradiotherapy in glioblastoma
Aly Ismailov, Poptsova M., Plos One 2026 Vol. 21 No. 9 Article e0355902
Added: October 2, 2026
Консервативные энтропийно и энергетически корректные разностные методы для одномерных квазигазодинамических систем уравнений
Zlotnik A., Математические заметки 2026 Т. 120 № 6 С. 1005–1009
Численным методам решения систем газодинамических уравнений посвящена обширная литература. Ранее было разработано и успешно апробировано специальное семейство симметричных по пространству  консервативных разностных методов, основанных на предварительной кинетической, точнее, квазигазодинамической (КГД), регуляризации этих уравнений. Актуальной задачей является построение численных методов, которые обладают не только свойством консервативности по массе, импульсу и полной энергии, но и удовлетворяют условиям энтропийной ...
Added: October 1, 2026
Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence (IJCAI 2026)
International Joint Conferences on Artificial Intelligence, 2026.
Added: October 1, 2026
Ensemble-based Prototype-Augmented Multimodal Fusion for Ambivalence/Hesitancy Recognition
Ryumina E., Aksenov A., Сысоев Д. С. et al., IEEE Computer Society, 2026.
Ambivalence/hesitancy recognition in unconstrained videos is a challenging problem due to the subtle, multimodal, and context-dependent nature of this behavioral state. In this paper, a multimodal approach for video-level ambivalence/hesitancy recognition is presented for the 10th ABAW Competition. The proposed approach integrates four complementary modalities: scene, face, audio, and text. Scene dynamics are captured with ...
Added: September 30, 2026
Decoding Algorithms for Binary U-UV Codes: A Unified Survey of Performance and Complexity
Ivanov F., Kotov F., IEEE Access 2026 Vol. 14 P. 104662–104679
U-UV codes, based on the Plotkin (U, U + V) construction, provide a unified framework that includes polar and Reed–Muller codes and enables flexible design through the choice of component codes. While modern capacity-approaching codes achieve excellent performance at large block lengths, their efficiency at short and moderate lengths remains limited, especially under low-latency constraints. ...
Added: September 30, 2026
The EG-TD3 Machine Learning Architecture: Evolutionary-Guided Twin Delayed Deep Deterministic Policy Gradient
Djambong Tenkeu H., Institute for System Programming of the RAS, 2026.
Added: September 29, 2026
Нижние множества и свойства замкнутости классов функций подсчета
Ivanashev Y., Доклады Российской академии наук. Математика, информатика, процессы управления (ранее - Доклады Академии Наук. Математика) 2026 Т. 529 С. 93–101
Язык L является нижним для релятивизируемого сложностного класса C, если CL=C. Для классов #P, GapP и SpanP известны точные нижние классы языков: Low(#P) = UP ∩ coUP, Low(GapP) = SPP и Low(SpanP) = NP ∩ coNP. В этой статье мы доказываем, что Low(TotP) = P, и приводим характеризации нижних классов функций для #P, GapP, TotP ...
Added: September 28, 2026
Role of dislocations in the mobility of pinned helium bubbles: Molecular dynamics simulations in aluminum
Piliugin L., Antropov A., Lobashev E. et al., Journal of Nuclear Materials 2026 Vol. 632 Article 156876
The effects of dislocations on the mobility of gas nanobubbles pinned to them are considered as novel unex- plored mechanisms of accelerated fission gas release and investigated using classical molecular dynamics of helium bubbles in FCC aluminum. Non-equilibrium methods are developed to calculate the mobility of a pinned bubble both along and across the dislocation ...
Added: September 28, 2026
MPI+OpenMP implementation of resolution-of-the-identity Hartree-Fock method exploiting permutational symmetry of three-center electron repulsion integrals
Kashpurovich I., Oleynichenko A., Stegailov V., Supercomputing Frontiers and Innovations 2026 Vol. 13 No. 1 P. 52–73
We report a high-performance implementation of the resolution-of-the-identity Hartree–Fock method that fully exploits the permutational symmetry of three-center electron repulsion integrals (ERI). The present implementation adopts a hybrid MPI+OpenMP parallelization strategy. Two different algorithmic approaches (with and without the pre-transformation of ERIs) are compared. A custom data layout introduced previously is employed. Designed to efficiently ...
Added: September 28, 2026
A Three-Party W-State Quantum Secret Sharing Protocol with X-Gate Encoding and Forbidden-Outcome Detection
Teregulov T., Loubenets E. R., / Series Quantum Physics "arXiv". 2026. No. 2609.31472.
We develop a new three-party quantum secret-sharing (QSS) protocol based on a three-qubit W state. This protocol encodes the secret-sequence bits using X gates and employs randomly selected Hadamard operations and measurement bases to generate information and security-test rounds. We evaluate the efficiency of the proposed protocol and analyze its security against an internal adversary ...
Added: September 28, 2026
Bytedance и Open Source - открытые проекты от разработчика TikTok
Silakov D., Системный администратор 2026 С. 84–89
Social media users rarely think about what lies behind the beautiful facade of activity feeds, teeming with photos and video stories. However, the widespread popularity of such platforms generates a huge amount of all sorts of content that needs to be stored, processed quickly, and displayed, and in the era of AI, it also needs ...
Added: September 28, 2026
Shape-aware deep learning for models of production
Prokhorov A., Wei Z., Sang H. et al., Journal of Productivity Analysis 2026 Vol. 65 P. 1–16
The stochastic frontier model (SFM) is widely employed in the analysis of productivity and efficiency, yet strict parametric forms, such as the Cobb-Douglas and Translog functions, are often assumed for modeling production, leading to potential misspecification issues. While semi- and nonparametric SFMs offer greater flexibility, they face challenges in imposing monotonicity and concavity to maintain ...
Added: September 28, 2026
Inverse quickest path problem on networks under weighted l_\infty norm
Qian X., Guan X., Zhang B. et al., Journal of Global Optimization 2026
Inverse quickest path problem on networks ...
Added: September 27, 2026
Navigating Complexity: Statistical Methods, Data Analysis, and Machine Learning for Actionable Insights
Switzerland: Springer Cham, 2026.
This volume gathers selected, peer-reviewed contributions presented at the 19th Conference of the International Federation of Classification Societies (IFCS 2026), held on 14–16 July 2026 in Milan, Italy. Reflecting the volume’s motto, Navigating Complexity – Statistical Methods, Data Analysis, and Machine Learning for Actionable Insights, the papers showcase modern methodologies and real-world applications designed to extract ...
Added: September 25, 2026
An early warning system for emerging markets
Kraevskiy A., Sokolovskiy E., Prokhorov A., Emerging Markets Review 2026 No. 74 P. 1–19
Financial markets of emerging economies are vulnerable to extreme and cascading information spillovers, surges, sudden stops and reversals. With this in mind, we develop a new online early warning system (EWS) to detect what is referred to as ‘concept drift’ in machine learning, as a ‘regime shift’ in economics and as a ‘change-point’ in statistics. ...
Added: September 25, 2026
Critical Success Factors for GenAI Digital Products: From Technology–Market Duality to a Technology–Market–Ethics Triad
Sorokin I., Tekic Z., Technology in Society 2026 Vol. 88 Article 103456
Generative AI (GenAI) digital products challenge established new product development and product success frameworks because performance after launch remains variable: outputs differ across runs and contexts, behavior can shift under drift, and realized value depends on user interaction, oversight, and governance at scale. Focusing on large language model (LLM)-based GenAI digital products, this study identifies ...
Added: September 23, 2026
FROM LECTURER TO CHATBOT: EVALUATING A HYBRID TEACHING MODEL
Ravedovskaya U., Didenko A., Филатова А. А., Journal of Teaching English for Specific and Academic Purposes 2025 Vol. 13 No. 3 P. 529–538
Emergence of generative artificial intelligence (GenAI) is revolutionizing teaching and evaluation in higher education. Early adopters have already demonstrated how large language model (LLM) conversational agents can serve as on-demand tutors, yet empirical evidence regarding their effectiveness in facilitating conceptual learning in non-computational domains is scant. Based on constructivist learning theory, this paper presents a ...
Added: September 18, 2026
Correcting or Rewriting? An Expert Evaluation of LLM-Based GEC on Academic Learner Data
Kopylova E.V., Tsegoeva O. G., Berlin V.A. et al., , in: Компьютерная лингвистика и интеллектуальные технологии: По материалам ежегодной международной конференции «Диалог». Выпуск 24Issue 24.: M.: Max press, 2026. Ch. 26 P. 1–10.
This paper investigates how large language models correct complex grammatical errors in Russian academic learner writing. Unlike traditional minimal-edit GEC systems, LLMs often apply generative rewriting strategies that may improve fluency, but risk structural overcorrection and semantic drift. We introduce a new expert benchmark derived from an authentic 3,1M-word learner corpus and construct an evaluation set annotated for ...
Added: June 27, 2026
Анализ культурных референций в творчестве А. Вознесенского: цифровое исследование имен персоналий
Tyuryakova-Matveeva D., Цифровые гуманитарные исследования 2026 № 1 С. 4–26
The article explores cultural references in the works of Andrei Voznesensky by analyzing the personalities he mentions. A total of 1,678 works were processed, including poetry, prose, and early unpublished poems. NER methods based on Natasha, spaCy, and LLM Grok tools made it possible to study the frequency of mentions of famous people and their ...
Added: May 31, 2026
  • 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