• A
  • A
  • A
  • АБВ
  • АБВ
  • АБВ
  • A
  • A
  • A
  • A
  • A
Обычная версия сайта
  • RU
  • EN
  • HSE University
  • Publications
  • Book chapter
  • DSNDM: Deep Siamese Neural Discourse Model with Attention for Text Pairs Categorization and Ranking
  • 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
June 5, 2026
Neural Network Maps as a Method for Constructing Mathematical Models
Scientists from HSE University–Nizhny Novgorod and the Institute of Physics Belgrade, Serbia, are jointly exploring the application of machine learning techniques and neural networks to the study of nonlinear dynamics. Natalya Stankevich, Leading Research Fellow at the Laboratory of Topological Methods in Dynamics of the Faculty of Informatics, Mathematics, and Computer Science at HSE University–Nizhny Novgorod, spoke to the HSE News Service about this international project.
June 5, 2026
‘In the Age of Technology, It Is Interesting to Look into the Past and Think about What We Can Take from It
Polina Tabakova decided to apply for a Philology degree at HSE in Nizhny Novgorod because she grew up in Mari El and did not want to move far away from the Russian forests. In an interview for the Young Scientists of HSE University project, she spoke about the genre of the campus novel, the existential drama of Kolobok, and a blackout version of Eugene Onegin.
June 5, 2026
HSE Scientists Develop Method to Compress Large Language Models Without Losing Quality
Researchers from the AI and Digital Science Institute at the HSE Faculty of Computer Science have developed a new compression method for large language models such as GPT and LLaMA that reduces their size by 25–36% without additional training or significant loss of accuracy. This is the first approach to use mathematical transformations—specifically, rotations of model weights—to make models more amenable to compression with structured matrices. The study results have been published in ACL Findings 2025. The code is available on GitHub.

 

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

?

DSNDM: Deep Siamese Neural Discourse Model with Attention for Text Pairs Categorization and Ranking

P. 76–85.
Chernyavskiy A., Ilvovsky D.

In this paper, the utility and advantages of the discourse analysis for text pairs categorization and ranking are investigated. We consider two tasks in which discourse structure seems useful and important: automatic verification of political statements, and ranking in question answering systems. We propose a neural network based approach to learn the match between pairs of discourse tree structures. To this end, the neural TreeLSTM model is modified to effectively encode discourse trees and DSNDM model based on it is suggested to analyze pairs of texts. In addition, the integration of the attention mechanism in the model is proposed. Moreover, different ranking approaches are investigated for the second task. In the paper, the comparison with state-of-the-art methods is given. Experiments illustrate that combination of neural networks and discourse structure in DSNDM is effective since it reaches top results in the assigned tasks. The evaluation also demonstrates that discourse analysis improves quality for the processing of longer texts.

Language: English
Full text
DOI
Text on another site
Keywords: attentionQuestion-Answering Systemsdiscourse structureFact-checkingrecursive neural networksiamese model
Publication based on the results of:
Intelligent Data Analysis in Interactive Systems for Transdisciplinary Applications (2020)

In book

Proceedings of the First Workshop on Computational Approaches to Discourse
Association for Computational Linguistics, 2020.
Similar publications
Исследование изменений вызванных потенциалов для целевых слуховых стимулов в условии эмоционального отвлечения
Пчелинцева М. Е., Lazarev I. E., Lyusin D., В кн.: Когнитивная наука в Москве: новые исследования. Материалы конференции 25 – 26 июня 2025.: М.: Буки Веди, 2025. С. 447–451.
The effects of emotional distraction might differ depending on the valence and arousal of induced affective states. Nevertheless, insufficient complexity of a cognitive task might affect the ability of participants to allocate attention resources for the successful examination of emotional stimuli and task performance. This is why, in previous research, indicators of accuracy and response ...
Added: January 16, 2026
Enhancing explainability in deepfake detection with graph attention networks
Aleksandr S. Pikul, Popov I., Безопасность информационных технологий 2025 Vol. 32 No. 2 P. 73–82
Understanding how artificial intelligence models make decisions is important, especially for difficult tasks like detecting deepfakes, where it's not enough to just get a result – it needs to know why the model made that choice. Many current methods, like Shapley additive explanations (SHAP) and Gradient-weighted Class Activation Mapping (Grad-CAM), help explain these decisions, but ...
Added: December 12, 2025
Verbal and Nonverbal Interference Modulate the Effect of Learned Inattention in Category Learning
Haider Z., Kotov A. A., Matyushkina V. I., , in: Когнитивная наука в Москве: новые исследования. Материалы конференции 25 – 26 июня 2025.: М.: Буки Веди, 2025. P. 31–36.
Added: December 1, 2025
Cognitive-digital interaction: the state of the field, weaknesses and solutions
Anufrieva A., Acta Psychologica 2025 Vol. 259 Article 105229
The present review aims to examine the current state of research in the field of cognitive-digital interaction (CDI). CDI is a field of fundamental research studying the regularities of cognitive processes under the influence of digital environment. The article defines key concepts, such as “cognitive system”, “environment”, and “artifact” and exploring theoretical frameworks for the ...
Added: August 1, 2025
Overload but guide: impact of environment saturation on attention and working memory under real and digital conditions
Anufrieva A., Gorbunova E. S., Психологические исследования: электронный научный журнал 2025 Vol. 18 No. 101 Article 6
The digital environment surrounds us everywhere. However, little is known about the differences between digital and real environments impact on cognitive functions. Initially, the present study aims to juxtapose attention and working memory (WM) under digital and real conditions. In Experiment 1, attention and WM were compared under real (paper) and digital (computer) conditions using ...
Added: July 9, 2025
Exploring Attention, Cognitive Load and Brain Connectivity During Music Listening
Provorova A., Kulikova S., , in: Schemas In Language, Music, And Visual Cognition: Book of Abstracts.: Niš: Faculty of Philosophy, University of Nis, 2024. P. 35–35.
The purpose of this research was to investigate the cognitive mechanisms underlying the ability to read musical notations. Reading musical notations requires efficient integration of auditory and visual stimuli. Such integration is likely to be provided by means of functional connectivity between different brain regions. Furthermore, it should require maintaining a certain level of continuous ...
Added: December 19, 2024
Functional models of elementary discursive units in Russian eSports commentary
Микулинский А. Д., , in: Синергия языков и культур 2022: междисциплинарные исследования.: St. Petersburg: -, 2023. P. 335–351.
The paper is devoted to the issue of the local structure modeling of the eSports commentary spoken genre on an example of the Dota 2 computer discipline. ESports commentary is a spontaneous and creative speech aimed at describing of what is happening on the computer-gaming field. The main factors that force us to study it ...
Added: May 12, 2024
GroundHog: Dialogue Generation using Multi-Grained Linguistic Input
Chernyavskiy A., Ostyakova L., Ilvovsky D., , in: Proceedings of the 5th Workshop on Computational Approaches to Discourse (CODI 2024).: Association for Computational Linguistics, 2024. P. 149–160.
Recent language models have significantly boosted conversational AI by enabling fast and cost-effective response generation in dialogue systems. However, dialogue systems based on neural generative approaches often lack truthfulness, reliability, and the ability to analyze the dialogue flow needed for smooth and consistent conversations with users. To address these issues, we introduce GroundHog, a modified ...
Added: May 9, 2024
Unleashing the Power of Discourse-Enhanced Transformers for Propaganda Detection
Chernyavskiy A., Ilvovsky D., Nakov P., , in: Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: (Volume 1: Long Papers).: Association for Computational Linguistics, 2024. P. 1452–1462.
Added: May 9, 2024
Crossmodal Plasticity, Sensory Experience, and Cognition
Vinogradova V., Cardin V., , in: Oxford Research Encyclopedia of Neuroscience.: Oxford University Press, 2024.
Crossmodal plasticity occurs when sensory regions of the brain adapt to process sensory inputs from different modalities. This is seen in cases of congenital and early deafness and blindness, where, in the absence of their typical inputs, auditory and visual cortices respond to other sensory information. Crossmodal plasticity in deaf and blind individuals impacts several ...
Added: March 25, 2024
Attentional and emotional brain response to message framing in context of green marketing
Zubair M., Wang X., Iqbal S. et al., Heliyon 2020 No. 6 P. 1–7
Background: Message framing plays an important role in advertising strategies and has been studied from various perspectives in different behavioral studies. New method: This study employs the event-related potential technique to examine attentional and emotional brain processing as influenced by message framing in the context of green marketing. Results: The behavioral results demonstrated that purchase preference was higher under positive ...
Added: December 29, 2023
Multimodal Discourse Trees in Forensic Linguistics
Galitsky B., Ilvovsky D., Goncharova E., , in: Компьютерная лингвистика и интеллектуальные технологии: По материалам ежегодной международной конференции «Диалог». Вып. 22.Вып. 22.: [б.и.], 2023.
We extend the concept of a discourse tree (DT) in the discourse representation of text towards data of various forms and natures. The communicative DT to include speech act theory, extended DT to ascend to the level of multiple documents, entity DT to track how discourse covers various entities were defined previously in computational linguistics, we now proceed ...
Added: November 10, 2023
Postural control in emotional states: an effect of biofeedback
Kosonogov V., Medvedeva A., Komilova F. et al., Gait and Posture 2024 Vol. 108 P. 183–188
Background Emotional states in the short term and affective impairments, such as anxiety and depression in the long run, can have a significant impact on postural control. Individuals with these conditions often struggle with maintaining balance during emotionally charged situations, which can increase their risk of falls and injuries. Biofeedback has been proposed as a ...
Added: October 26, 2023
Transformer-based Multi-Party Conversation Generation using Dialogue Discourse Acts Planning
Alexander Chernyavskiy, Ilvovsky D., , in: Proceedings of the 24th Meeting of the Special Interest Group on Discourse and Dialogue.: Association for Computational Linguistics, 2023. P. 519–529.
Recent transformer-based approaches to multi-party conversation generation may produce syntactically coherent but discursively inconsistent dialogues in some cases. To address this issue, we propose an approach to integrate a dialogue act planning stage into the end-to-end transformer-based generation pipeline. This approach consists of a transformer fine-tuning procedure based on linearized dialogue representations that include special ...
Added: October 6, 2023
Особенности внимания, влияющие на успешность овладения жестовым языком у взрослых с нормальным слухом
Ясин М. И., Vinogradova V., Психолог 2018 No. 4 P. 46–54
Изучение новых языков активно задействует когнитивные навыки. Это двухсторонней процесс: обучение влияет на познавательные функции, успешность обучения зависит от познавательных способностей и навыков. Жестовый язык глухих – особый язык, так как он разворачивается в непривычных для слышащих людей визуальной и кинестетической модальностях. Целью работы было изучить особенности внимания, которые играют ключевую роль в успешном овладении ...
Added: September 7, 2023
Increased error rate and delayed response to negative emotional stimuli in antisaccade task in obsessive-compulsive disorder
Guzal Khayrullina, Martynova O., Elizaveta P., International Journal of Psychophysiology 2023 No. 192 P. 62–71
Ample evidence links impaired inhibitory control, attentional distortions, emotional dysregulation, and obsessive-compulsive disorder (OCD). However, it remains unclear what underlies the deficit that triggers the OCD cycle. The present study used an antisaccade paradigm with emotional valences to compare eye movement patterns reflecting inhibitory control and attention switching in OCD and healthy control groups. Thirty-two patients with OCD and ...
Added: August 23, 2023
Attention sustainability and shifting in the digital environment
Anufrieva A., Gorbunova E. S., Perception 2021 Vol. 50 No. 1S P. 69–69
The digital environment surrounds us everywhere and influences our cognitive system. Very few studies aimed to find mechanisms of how the digital environment influences visual attention. In two experiments, we attempted to investigate how the complexity of the digital environment affects visual attention and user’s performance. Attentional sustainability and shifting were measured in “simple” and “complex” conditions. Participants were presented with an online ...
Added: May 10, 2023
Paul Ricoeur on the Recognition of Anxiety: Phenomenological Hermeneutics in Action
Khan K., Вестник Российского университета дружбы народов. Серия: Философия 2021 Vol. 25 No. 3 P. 470–482
The philosophical concept of anxiety, which is usually associated with Kierkegaard and Heidegger's existential philosophy, seems to be an underestimated notion in Paul Ricoeur's phenomenological hermeneutics, while its role is important - anxiety appears to serve as the grounding for hope in his hermeneutics of self. The article aims to show how the anxiety is ...
Added: February 28, 2023
The Influence of Happiness and Anxiety on Emotional Stroop Effect
Martynova E., Shakirova S. A., Lyusin D., / NRU Higher School of Economics. Series PSY "Psychology". 2022. No. 131.
The main aim of this study was to examine how happiness and anxiety influence emotional Stroop effect. According to the principle of emotion congruence, information processing is facilitated if its emotional tone matches an individual’s mood. The first hypothesis suggested that emotional Stroop effect would be greater with stimuli incongruent with a participant’s emotional state. ...
Added: June 14, 2022
Correcting Texts Generated by Transformers using Discourse Features and Web Mining
Chernyavskiy A., Ilvovsky D., Galitsky B., , in: Proceedings of the Student Research Workshop Associated with RANLP 2021.: INCOMA Ltd, 2021. P. 36–43.
Recent transformer-based approaches to NLG like GPT-2 can generate syntactically coherent original texts. However, these generated texts have serious flaws: global discourse incoherence and meaninglessness of sentences in terms of entity values. We address both of these flaws: they are independent but can be combined to generate original texts that will be both consistent and ...
Added: May 29, 2022
Improving Text Generation via Neural Discourse Planning
Alexander Chernyavskiy, , in: WSDM 2022 - Proceedings of the 15th ACM International Conference on Web Search and Data Mining.: Association for Computing Machinery (ACM), 2022. P. 1543–1544.
Recent Transformer-based approaches to NLG like GPT-2 can generate syntactically coherent original texts. However, these generated texts have serious flaws. One of them is a global discourse incoherence. We present an approach to estimate the quality of discourse structure. Empirical results confirm that the discourse structure of currently generated texts is inaccurate. We propose the ...
Added: May 29, 2022
  • 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