• A
  • A
  • A
  • АБВ
  • АБВ
  • АБВ
  • A
  • A
  • A
  • A
  • A
Обычная версия сайта
  • RU
  • EN
  • HSE University
  • Publications
  • Articles
  • Less is More: Instructed Text Simplification for People with Aphasia
  • 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
November 17, 2026
Physicists Show How a Solvent Shapes the Response of Drug Molecules
Many drug molecules can switch between different three-dimensional shapes. Using a mathematical model of ibuprofen dissolved in supercritical CO₂, researchers from HSE University and the Institute of Solution Chemistry of the Russian Academy of Sciences have shown that the solvent can make these molecules appear to respond unusually slowly. The molecules themselves continue to change shape rapidly, but their surroundings rearrange much more slowly, and this lag shows up in the measurements. The study has been published in The Journal of Chemical Physics. 
November 10, 2026
Physicists Train AI to Optimise Particle Beams in Accelerators
Researchers from the AI and Digital Science Institute at the HSE Faculty of Computer Science and the Budker Institute of Nuclear Physics at the Siberian Branch of the Russian Academy of Sciences have developed RLABC (Reinforcement Learning for Accelerator Beamline Control), a framework that uses reinforcement learning to identify optimal settings for a particle accelerator. In a computer simulation, RLABC optimised the accelerator's parameters to achieve a particle transmission rate of 70%. The study has been published in Computer Physics Communications.
November 9, 2026
'Organ-on-a-Chip Technology Could Eliminate the Need for Animal Testing'
The Laboratory of Molecular Physiology at the HSE Faculty of Biology and Biotechnology investigates how molecular regulators known as microRNAs control gene expression and contribute to the development of diseases, including cancer, viral and inflammatory conditions, and pregnancy complications. At HSE University, researchers develop organ-on-a-chip models: miniature devices containing living cells that mimic the functions of human organs, such as the placenta and intestines. These models help researchers understand how diseases develop and how drugs affect them. HSE News Service spoke with Evgeny Knyazev, Head of the Laboratory.

 

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

?

Less is More: Instructed Text Simplification for People with Aphasia

Aphasiology. 2026.
Kolmogorova A., Anastasia Margolina, Telnova A., Popljujkova H.

Background: Patients with aphasia experience significant difficulties in reading and comprehending texts. Nevertheless, text-based activities constitute a substantial part of speech therapy programs for these patients –  speech-language pathologists assign tasks such as reading texts aloud, answering comprehension questions, and, in cases of mild impairment, retelling the content. However, the textual material used must be adapted to the patients' linguistic and cognitive abilities, and this presents a challenge for clinicians: on the one hand, the texts should be engaging, relevant to the patient's life experiences, and personally motivating, while on the other hand, adapting them to the patient's capabilities requires considerable time and effort. To address this issue, we have developed a methodology for the automatic simplification of texts for speech therapy in individuals with aphasia.

Aims: The aim of this study is to investigate the effectiveness of using Large Language Models (LLMs) for multilevel text simplification for patients with aphasia. 

Methods: A parallel corpus consisting of 134 texts divided into 1010 sentences in Russian was prepared. Using guidelines developed by speech therapists specializing in complex motor aphasia eight Russian-speaking annotators generated three simplified versions for each original sentence, corresponding to three levels of disease severity. Our designed multi-tiered instructions and a dataset comprising 100 original-to-simplified text pairs were used in a few-shot prompting strategy applied to four LLMs, which were then tasked with simplifying the texts. 

Outcomes and Results: Models were evaluated using (1) linguistic complexity metrics and (2) BERTScore for semantic similarity. The top LLM's output was clinically validated with 12 complex motor aphasia patients. Patients read six texts (three auto-simplified, three manual), then answered questions or retold stories. Automated texts scored higher in “interestedness” but slightly lower in “easiness” versus manual versions.

Conclusions: Findings indicate that few-shot prompted automated simplification effectively adapts texts for complex motor aphasia patients. Automated versions showed comparable linguistic complexity and high semantic fidelity to originals. While marginally less comprehensible than manual simplifications, patients rated them as more engaging.


 

Research target: Philology and Linguistics
Language: English
Full text
DOI
Keywords: speech therapyaphasiaLarge Language Modelspromptingautomatic speech simplification
Publication based on the results of:
Linguistic and cognitive diversity in formal models, computer tools, and educational resources (2025)
Similar publications
«Сохрани мою речь...». Мандельштамовский альманах.
Свет, 2026.
Мандельштамовское общество в сотрудничестве с Центром цифровых архивных исследований Школы филологических наук Научно-исследователь ского университета «Высшая школа экономики» возобновляет выпуск серии традиционных Мандельштамовских альманахов «Сохрани мою речь...». Ранее серия под эгидой Мандельштамовского общества выходила в издательствах «Обновление» (1991, выпуск 1), «Книжный сад» (1994, выпуск 2) и РГГУ (2000, 2008, 2011, выпуски 3–5). Шестой выпуск посвящен ...
Added: November 17, 2026
An Awkward Oikonym: Obscene Toponymy and Traditional Culture
Moroz A., Folklore (Estonia) 2026 Vol. 101 P. 441–456
Abstract. The article examines the situation surrounding an informal yet widely known and historically attested oikonym derived from an obscene word. On the one hand, the existence of this obscene oikonym serves as a point of pride and a unusual peculiarity, eagerly shared with ‘outsiders’ by locals. On the other hand, it makes the residents ...
Added: November 16, 2026
Вокруг Иосифа Бродского: неподцензурная литература 1950-х — 1970-х годов: материалы II международной конференции 28–29 мая 2025 года, Санкт-Петербург / сост. О.Л. Лейкинд. СПб.: ООО «Журнал «Звезда», 2026
Penskaja E., СПб.: СПб.: ООО «Журнал «Звезда», 2026.
The collection includes articles by authoritative literary scholars—participants in the Second International Scholarly Conference “Around Joseph Brodsky: Uncensored Literature of the 1950s–1970s,” held in May 2025 in St. Petersburg. The collection is divided into two sections. The first section—“Joseph Brodsky: Biography and Creative Work in the Context of His Time”—is devoted to the life and ...
Added: November 15, 2026
Этнолингвистика. Ономастика. Этимология. Материалы VI Международной научной конференции, посвященной 100-летию со дня рождения А. К. Матвеева. Екатеринбург, 24–27 сентября 2026 г.
Moroz A., Издательство Уральского университета, 2026.
The field materials obtained through many years of work by folklore expeditions of RSUH and HSE University in various regions of Russia and the eastern regions of Belarus contain a large number of relatively uniform contexts in which an informant tells a story about events involving the manifestation of a demonological character, the manifestation of ...
Added: November 14, 2026
О чем говорит школьный урок? Корпусный анализ структуры урока и речи учителя как основа для педагогических продуктов
Виноградова Ю. С., Браташ В. С., Zubov V. et al., Вопросы образования 2026 Т. 1 № 3 С. 94–131
The aim of the study is to describe the structure of a school lesson and identify linguistic characteristics associated with effective teaching practices, based on recordings of real lessons in schools of the Russian Federation. Fifty-five audio recordings of lessons (Grades 5–9, six subjects, 2022–2024) were annotated for lesson structure, phonetic, lexical, and grammatical features, ...
Added: November 13, 2026
Берестяные грамоты из раскопок 2024 г. II. Великий Новгород, Старая Русса, Меглецы
Gippius A., Вопросы языкознания 2026 № 6 С. 7–26
This article presents a preliminary publication of 14 birchbark letters discovered during the 2024 archaeological season in Veliky Novgorod. Of particular historical and linguistic interest is a group of seven documents from the second half of the 14th century attributed to scribe Fefila, who was associated with posadnik Ontsifor Lukinich. It includes, in particular, court ...
Added: November 13, 2026
Thematic Clusters and Linguistic Features of Fashion Anglicisms Used by Russian Fashion Influencers
Karamalak O., Dionysios Zoumpalidis, English Today 2026 P. 1–11
The study explores the use of Anglicisms in the discourse of Russian speaking fashion influencers on YouTube, focusing on the thematic usage and linguistic adaptation of English borrowings to the Russian language. This topic is highly relevant due to the unprecedented popularity of digital social media and influencers who manipulate consumers’ opinions. Research methodology implies ...
Added: November 12, 2026
«Пролитая чаша» (Театр сатиры, 1952): нарративная адаптация и стилизация китайской классики как опыт межкультурного диалога
Чэнь Б., Penskaja E., Театр. Живопись. Кино. Музыка 2026 № 1 С. 150–162
Based on a  wide range of unpublished archival documents the article presents a comprehensive philological and historical-theatrical analysis of the first Soviet production of the classical Chinese drama The Western Chamber (Wang Shifu, 13th century) — the play The Spilled Cup (Moscow Satire Theatre, 1952, dir. N. V. Petrov and V. N. Pluchek, adaptation by A. P. Globа). ...
Added: November 11, 2026
“A Nursery of Technique,” the Laboratory in the Socio-Cultural Context of the 1920s–1930s: Between Practice and Metaphor
Penskaja E., Arts 2026 Vol. 15 No. 7 P. 172–203
This article analyzes the laboratory discourse in Soviet society during the first third of the twentieth century through the lens of tékhnē—the ancient fusion of making and knowing—arguing that the laboratory became a key site for redefining artistic practice as a form of knowledge production. Drawing on the institutional critique of the laboratory (Bruno Latour), ...
Added: November 11, 2026
"Подопытный". Сергей Петров и Осип Мандельштам
Penskaja E., "Сохрани мою речь..." Мандельштамовский альманах 2026 № 6 С. 206–219
This paper  is about the meeting between Nadezhda Yakovlevna Mandelstam and Sergei Vladimirovich Petrov (1911–1988), a poet, translator, and prose writer.³ He had been through prison and exile; after rehabilitation he taught foreign languages, and from 1960 he led a seminar of Scandinavianists in the literary translation section of the Leningrad branch of the Writers’ ...
Added: November 11, 2026
Латерализация функциональной гемодинамики мозга у детей раннего возраста как предиктор расстройств развития языка и речи: обзор литературы
Kibardina A., Vinogradova V., Alexeeva S. V. et al., Вопросы современной педиатрии 2026 Т. 25 № 6 С. 0–0
Проблема ранней диагностики расстройств развития языка и речи сохраняет актуальность в педиатрии. Успешность абилитации при таких расстройствах определяется ранним началом абилитационных мероприятий, но собственно речевые признаки дизонтогенеза в раннем возрасте (0-5 лет) еще недостаточно информативны для инициации вмешательства. По этой причине интерес представляют предикторы расстройств развития языка и речи, доступные для измерения на ранних этапах речевого развития. ...
Added: November 11, 2026
The Syriac Story of the Body of John the Baptist: A Newly Discovered Parabiblical Composition
Minov S., Bible and Christian Antiquity 2026 Vol. 8 No. 1 P. 15–59
The article presents the editio princeps, translation, and commentary of a newly discovered parabiblical composition attested thus far only in Syriac: the Story of the Body of John the Baptist. Produced during the Islamic period in the East Syrian milieu, this work offers a detailed account of John’s life and death, as well as the ...
Added: November 10, 2026
Laughter and Humour among Syriac Christians: Prolegomena for Cultural History
Minov S., Scrinium: Journal of Patrology and Critical Hagiography 2026 Vol. 22 P. 145–193
The article surveys the most significant expressions of laughter and humor in Syriac Christian culture before the modern period. Starting with a general discussion of the dichotomy between the “high” and “low” cultures of laughter, it proceeds to examine various manifestations of gelastic discourse across different textual corpora: monastic and hagiographic literature from Late Antiquity, ...
Added: November 10, 2026
EdFitter: a hybrid course recommendation system using large language models
Sergei Koltcov, Ryumin D., Alexandr Axyonov et al., PeerJ Computer Science 2026 Article 12:e4141
Educational institutions face increasing pressure to adapt their curricula to the rapidly evolving demands of the job market, and recommender systems can be important tools to guide students in selecting courses that align with their career goals. We present EdFitter, a hybrid course recommendation system that combines pretrained text embeddings for retrieval with large language ...
Added: November 10, 2026
PrimeKV: Preserving critical KV cache without attention scores for long-context inference
Zhang Z., Ilvovsky D., Neurocomputing 2027 Vol. 710
Efficient management of the Key-Value (KV) cache is essential for deploying large language models (LLMs) in long-context scenarios, where memory requirements often exceed the capacity of resource-constrained hardware. Many existing training-free compression algorithms typically rely on attention-driven heuristics, but exhibit two key limitations. First, they require explicit attention score computation, which is difficult to reconcile ...
Added: November 5, 2026
Amplifying Latent Safety in Large Language Models via Gated Activation Steering
Roman Prosvirnin, Suslov A., Aleksei Soldatov et al., Computation 2026 Vol. 14 No. 10 Article 261
Abstract Safety-aligned language models often encode that a request is harmful yet still comply with it. We turn this gap between internal recognition and observable behavior into an inference-time defense. The proposed activation-steering method uses a multiplicative operator that amplifies the residual-stream component along a harm-recognition direction. Intervention strength scales with the model’s own assessment of ...
Added: October 27, 2026
Gamification of Literary Classics Using Large Language Models: Developing a Digital Assistant for the Secondary School Literature Course
Kolmogorova A., Seredina D. A., Herald of the Russian Academy of Sciences 2026 No. 96 P. 24–32
The relevance of this study is determined by the challenge of integrating large language models (LLMs) into language pedagogy, specifically for gamifying the process of studying Russian classical literature and fostering reading motivation among high school students. This study aims to develop and test a digital assistant, powered by an LLM, designed to gamify the ...
Added: August 31, 2026
ML²B: Benchmarking LLMs on Cross-Lingual ML Pipeline Generation
Trofimova E., Shamina Z., Selifanova M. et al., , in: Proceedings of the Generative Code Intelligence Workshop (GeCoIn 2026), co-located with the 35th International Joint Conference on Artificial Intelligence (IJCAI-ECAI 2026)Vol. 4238.: CEUR-WS.org, 2026.
We introduce ML2B, the first benchmark for evaluating cross-lingual task comprehension in end-to-end ML pipeline generation by large language models. Despite growing global AI adoption, no systematic evaluation exists for ML pipeline generation beyond English task descriptions. ML2B addresses this gap with 35 Kaggle competitions spanning tabular, text, and image domains, translated into 14 languages ...
Added: August 20, 2026
A Multimodal Framework for Aphasia Severity Classification in Russian
Kolmogorova A., Ekaterina Yavshits, Anastasia Margolina et al., , in: Proceedings of the 1st Workshop on Linguistic Analysis for Health (HeaLing 2026).: Association for Computational Linguistics, 2026. P. 257–265.
Automatic classification of aphasia severity presents persistent challenges, particularly for languages with limited clinical speech resources such as Russian. This paper explores a multimodal approach to severity estimation that combines acoustic and semantic representations of pathological speech. Acoustic features are extracted using pretrained Wav2Vec 2.0 models, while semantic information is obtained from the encoder of ...
Added: August 19, 2026
Improving Differential Equation Solving in Compact Language Models via Activation Steering and Reinforcement Learning
Surkov A., Ignatenko V., Koltsov S., Computers, Materials and Continua 2026 Vol. 88 No. 3 Article 74
Large language models have recently demonstrated promising capabilities in mathematical reasoning; however, their performance on tasks requiring strict symbolic manipulation, such as solving differential equations, remains limited, especially for compact models. In this work, we investigate whether activation steering combined with reinforcement learning can improve the quality of solutions generated by pretrained language models without ...
Added: July 8, 2026
Когда чаще не значит лучше: сценарии использования генеративного ИИ в высшем образовании
Tarasova K., Talov D., Ivanova A., Высшее образование в России 2026 Т. 35 № 6 С. 127–148
The article examines the relationship between the use of generative artificial intelligence in learning and several AI-related characteristics of students at Russian universities. The study is based on the assumption that the frequency of AI use should not be treated as a direct indicator of AI literacy or competence in working with generative systems. Four ...
Added: June 29, 2026
Университетский глоссарий локальной универсальности: сталактиты, сталагмиты, сталагнаты производства социального знания
Ganzha A. G., Жиганов М. Д., Пути России. Журнал cоциальных и этнографических исследований 2026 Т. 4 № 2 С. 145–170
This article is structured as a small glossary of observational essays on Russian university and academic life, summarizing the experiences of its participants over the past several years. It examines this life from the perspective of the dynamics of social knowledge, its content, form, organization, structure, as well as the maintenance of its stability and ...
Added: May 27, 2026
COALA: Numerically Stable and Efficient Framework for Context-Aware Low-Rank Approximation
Parkina U., Rakhuba M., , in: 39th Conference on Neural Information Processing Systems (NeurIPS 2025).: NeurIPS, 2025. P. 71014–71041.
Recent studies suggest that context-aware low-rank approximation is a useful tool for compression and fine-tuning of modern large-scale neural networks. In this type of approximation, a norm is weighted by a matrix of input activations, significantly improving metrics over the unweighted case. Nevertheless, existing methods for neural networks suffer from numerical instabilities due to their ...
Added: April 29, 2026
Aphasia in Andrei Bely's Petersburg
Zolotareva O., Studies in the Novel 2025 Vol. 57 No. 1 P. 40–60
This essay is interested in how a novel behaves when it has been theorized out of existence by its own creator. I take as my case study the novel Petersburg, whose author, the prominent Russian modernist Andrei Bely, criticized the arts (including the art of literature) on ethical grounds. I argue that the tension between Bely's ...
Added: January 2, 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