• A
  • A
  • A
  • АБВ
  • АБВ
  • АБВ
  • A
  • A
  • A
  • A
  • A
Обычная версия сайта
  • RU
  • EN
  • HSE University
  • Publications
  • Book chapter
  • Shrink the Longest: Improving Latent Space Isotropy with Simplicial Geometry
  • 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
May 22, 2026
HSE Graduates AI Project Wins at TECH & AI Awards
Daria Davydova, graduate of the HSE Graduate School of Business and Head of the AI Implementation Unit at the Artificial Intelligence Department of Alfa-Bank, received a prize at the TECH & AI Awards. She was awarded for the best AI solution for optimising business processes. The winners were determined as part of the VII Russian Summit and Awards on Digital Transformation (CDO/CDTO Summit & Awards).
May 20, 2026
HSE University Opens First Representative Office of Satellite Laboratory in Brazil
HSE University-St Petersburg opened a representative office of the Satellite Laboratory on Social Entrepreneurship at the University of Campinas in Brazil. The platform is going to unite research and educational projects in the spheres of sustainable development, communications and social innovations.
May 18, 2026
The 'Second Shift' Is Not Why Women Avoid News
Women are more likely than men to avoid political and economic news, but the reasons for this behaviour are linked less to structural inequality or family-related stress than to personal attitudes and the emotional perception of news content. This conclusion was reached by HSE researchers after analysing data from a large-scale survey of more than 10,000 residents across 61 regions of Russia. The study findings have been published in Woman in Russian Society.

 

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

?

Shrink the Longest: Improving Latent Space Isotropy with Simplicial Geometry

P. 120–130.
Kudrjashov S., Karpik O., Klyshinskiy E.
Language: English
Full text
DOI
Text on another site
Keywords: Topological data analysisBERTisotropyLatent space geometry

In book

Analysis of Images, Social Networks and Texts, 12th International Conference, AIST 2024, Bishkek, Kyrgyzstan, October 17–19, 2024, Revised Selected Papers
Vol. 15419. , Springer, 2024.
Similar publications
Development of a Language Model for Automated Classification of English-Language Scientific Articles by SRSTI Codes
V. V. Zunin, A. I. Afonin, V. I. Anoshin et al., Automatic Documentation and Mathematical Linguistics 2025 Vol. 59 No. 5 P. 287–293
The development of an artificial intelligence-based language model for classifying English-language scientific articles by SRSTI codes is described. This improves the processes of reviewing and indexing scientific publications. A pre-processed dataset of scientific articles was used for training and testing the models. An architecture for cascade classification was developed, and the performance of models with ...
Added: February 11, 2026
Blurred Magnitude Homology of Functional Connectome for ASD Diagnosis
Alexander Kachura, Vsevolod Chernyshev, Kachan O. et al., Frontiers in Psychiatry 2026 Vol. 16 Article 1677282
Autism spectrum disorder (ASD) is one of the most common neurodevelopmental disorders. Existing studies show that adults with ASD may experience accelerated or altered neurocognitive aging. Consequently, cognitive decline in people with ASD can be delayed if timely measures are taken to treat this disorder. This study focuses on the development of a new algorithm ...
Added: January 21, 2026
A Language and Its Holes: The First-Order Homology of the Large-Scale Geometrical Structure of a Natural Language
Vasilii A. Gromov, Dang Q. N., Asel S. Erbolova, Complexity 2025 Vol. 2025 No. 1 Article 9659172
The present paper employs topological data analysis methods to reveal ‘holes’ (stable persistent homologies) in the semantic spaces of words, bigrams, and trigrams of the English and Russian languages, and to ascertain their boundaries. Furthermore, the paper selects those holes that belong to the large‐scale (coarse‐grained) structure of the language that are not just local ...
Added: November 11, 2025
A Feature Engineering Framework for Computer Vision Based on Topological Data Analysis
Абрамов А. С., Chernyshev V. L., Mikhaylets E. et al., / Series Social Science Research Network "Social Science Research Network". 2025.
Computer vision is one of the most relevant modern research areas with broad practical applications. However, traditional solutions based on deep learning have signicant limitations and can be misleading. Topological data analysis, on the other hand, is a modern approach to solving similar problems using mathematically deterministic methods of algebraic topology that reduce the risk ...
Added: September 23, 2025
Индекс этичности российских банков на основе искусственного интеллекта
Storchevoy M., Parshakov P., Paklina S. et al., Доклады Российской академии наук. Математика, информатика, процессы управления (ранее - Доклады Академии Наук. Математика) 2024 Т. 520 № 6 С. 70–81
Measuring a company's ethics is an important element in the mechanism of regulating the behavior of market participants, as it allows consumers and regulators to make better decisions, which has a disciplining effect on companies. We tested various methods of machine analysis of consumer feedback from Russian banks and developed an Ethics Index that allows ...
Added: October 31, 2024
The More Polypersonal the Better - A Short Look on Space Geometry of Fine-Tuned Layers
Sergei Kudriashov, Veronika Zykova, Stepanova A. et al., , in: Advances in Neural Computation, Machine Learning, and Cognitive Research VIII, Selected Papers from the XXVI International Conference on Neuroinformatics, October 21-25, 2024, Moscow, RussiaVol. VIII.: Cham: Springer, 2024. P. 13–22.
The interpretation of deep learning models is a rapidly growing field, with particular interest in language models. There are various approaches to this task, including training simpler models to replicate neural network predictions and analyzing the latent space of the model. The latter method allows us to not only identify patterns in the model’s decision-making process, but also understand ...
Added: October 24, 2024
A Language and Its Dimensions: Intrinsic Dimensions of Language Fractal Structures
Vasilii A. Gromov, Nikita S. Borodin, Asel S. Yerbolova, Complexity 2024 Vol. 2024 No. 1 Article 8863360
Te present paper introduces a novel object of study, a language fractal structure; we hypothesize that a set of embeddings of all n-grams of a natural language constitutes a representative sample of this fractal set. (We use the term Hailonakea to refer to the sum total of all language fractal structures, over all n). Te ...
Added: June 29, 2024
Axiomatic Foundation of Central Place Theory: Revision from the Standpoint of the Russian School
R. V. Dmitriev, Shuper V. A., Regional Research of Russia 2023 Vol. 13 No. 4 P. 751–757
The article refines the axiomatic foundation of central place theory (CPT) and identifies the possibilities and limitations of a logical transition in research from real settlement systems to central place (CP) systems. The necessity of relying on the CPT axioms in the following form is determined: (1) the space of a CP system is not ...
Added: February 16, 2024
Regional inflation analysis using social network data
Shcherbakov, V., Karpov I., Economy of Regions 2024 Vol. 20 No. 3 P. 930–946
Inflation is one of the most important macroeconomic indicators that have a great impact on the population of any country and region. Inflation is influenced by range of factors, one of which is inflation expectations. Many central banks all over the World take this factor into consideration while implementing monetary policy within the inflation targeting ...
Added: December 7, 2023
Grammar in Language Models: BERT Study
Chistyakova K., Kazakova Tatiana, / NRU HSE. Series WP BRP "Linguistics". 2023. No. 115.
The problem of language models’ interpretation is extensively inspected, but no universal answers have been found. Our study offers to combine widely accepted probing methods with a novel approach to a neural network under investigation. We propose to break grammatical forms on the pre-training step in order to get two "sibling" models, as it casts ...
Added: November 29, 2023
Classification of Short Scientific Texts
I. K. Kusakin, Fedorets O. V., A. Y. Romanov, Scientific and Technical Information Processing 2023 Vol. 50 No. 3 P. 176–183
This paper discusses modern approaches to natural language processing and the application of machine learning models to the task of classifying short scientific texts in Russian. This study is devoted to the analysis of methods for vectorization of textual information, selection of a model for scientific paper clas- sification, and training of linguistic model BERT ...
Added: November 4, 2023
Identifying and Visualizing Trends in Science, Technology, and Innovation Using SciBERT
Lobanova P., Bakhtin P., Sergienko Y., IEEE Transactions on Engineering Management 2024 No. 71 P. 11898–11906
Identification of science, technology, and innovation trends is a critical topic both for the scientific community and for companies that develop technologies, work on science and technology policy or invest in high tech. In this research authors demonstrate a novel approach implemented in iFORA system (developed by National Research University Higher School of Economics) using ...
Added: September 8, 2023
How to detect propaganda from social media? Exploitation of semantic and fine-tuned language models
Malik M. S., Imran T., Mona Mamdouh J., PeerJ Computer Science 2023 Vol. 9 Article e1248
Online propaganda is a mechanism to influence the opinions of social media users. It is a growing menace to public health, democratic institutions, and public society. The present study proposes a propaganda detection framework as a binary classification model based on a news repository. Several feature models are explored to develop a robust model such ...
Added: September 4, 2023
Automated defect identification for cell phones using language context, linguistic and smoke-word models
Muhammad Z. Y., Malik M. S., Ignatov D. I., Expert Systems with Applications 2023 Vol. 227 Article 120236
Product defects are a widespread concern for manufacturers when conducting quality and customer relationship management. Prior approaches addressed many electronic products however cell phones are still unexplored. Moreover, prior work mainly focused on the lexicon, probabilistic graphic, failure mode, and effect analysis models but the utilization of word embeddings and language models are not explored. State-of-the-art contextual word embeddings and language models generate automated features and ...
Added: June 13, 2023
Computational Experiments on Detecting Meaning shift in Jokes
Eugeniia Zakovorotnaia, , in: 2022 IEEE International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON).: Ekaterinburg: IEEE, 2022. P. 840–843.
The paper describes an experimental approach to detect the meaning shift, one of the most fundamental characteristics of humor, which is studied by many scientists in different interdisciplinary theoretical methodologies. We measured cosine similarity between setups and punchlines and explained these results through the set of objective criteria such as cosine results limitations, punchline length, ...
Added: May 10, 2023
Acceptability Judgements via Examining the Topology of Attention Maps
Cherniavskii D., Tulchinskii E., Mikhailov V. et al., , in: Findings of the Association for Computational Linguistics: EMNLP 2022.: Association for Computational Linguistics, 2022. Ch. 7 P. 88–107.
Added: February 17, 2023
  • 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