International Seminar. 2025 Season

A Place Where Human Language and Algorithms Engage in Dialogue

Explore Cutting-Edge Research and Innovations

in the Field of Language Technology

Attend the seminar

CompLing Seminar

June 23-26, 2025

CompLing-2025 seminar explores cutting-edge research in computational linguistics, NLP, and AI, fostering collaboration between researchers and industry to drive innovation and interdisciplinary exchange.

Zakharov.day

March 13, 2025

The meetup dedicated to the issues of automatic text processing, the creation and application of corpus resources, and continuing the research traditions established by the founder of the St. Petersburg School of Corpus Linguistics, V.P. Zakharov.

TextMining.day

Date to be announced

Which intersection of entities will you choose for your project? Let's piece the puzzle together and explore areas like sentiment analysis, semantic modeling, and other methods we use to uncover meaning in texts.

LLM.day

Date to be announced

What challenges do we face in building large language models? From managing massive datasets to tackling high fine-tuning costs and addressing data privacy concerns, creating your own LLM is no small feat. Join us to discuss these hurdles and discover how LLMs are transforming the way we approach AI across industries.

Previous Slide
Next Slide

Program: Computational Linguistics Seminar

← Session 1 - Russian track (23 June, 12:30-14.00, Room 1222) →

Геометрия падежей в векторных моделях русского языка
Кирилл Черников, Илья Суров
Университет ИТМО
Разработка системы анализа разноплановых характеристик поэтического текста
Арина Панкова, Елена Ягунова
Санкт-Петербургский государственный университет
Динамика тем научных статей в корпусе текстов по компьютерной и корпусной лингвистике
Ольга Митрофанова
Санкт-Петербургский государственный университет
Речевые тактики в ситуации конфликта в межличностном общении как составляющая языковой модели в системах искусственного интеллекта
Ольга Сытник
Санкт-Петербургский горный университет императрицы Екатерины II
Проблемы исследования словообразовательного потенциала с использованием современных поисковых систем
Елена Васильева
Иркутский государственный университет
Технологии векторного поиска при работе с цифровыми собраниями
Влада Погожельская
Национальный исследовательский университет «Высшая школа экономики»

← Session 2 - Russian track (23 June, 15:00-17.00, Room 1222) →

Использование алгоритмов машинного перевода в задаче субтитрирования образовательного видеоконтента
Екатерина Лаврентьева, Марина Коган
Санкт-Петербургский политехнический университет Петра Великого
Сравнение нейросетевых синтаксических анализаторов для русского языка
Елена Шамаева
Московский государственный университет имени М. В. Ломоносова
Оценка лингвистической компетенции больших языковых моделей
Ксения Студеникина, Екатерина Лютикова, Анастасия Герасимова
Московский государственный университет имени М. В. Ломоносова
Генерация фан-литературы на русском языке
Дарья Середина
Национальный исследовательский университет «Высшая школа экономики»
Сравнительный анализ методов настройки генеративных языковых моделей
Елизавета Сытикова, Мария Сергеева, Анастасия Колмогорова
Национальный исследовательский университет «Высшая школа экономики»
Большая языковая модель и человек рассматривают живопись
Полина Налобина, Анастасия Колмогорова
Национальный исследовательский университет «Высшая школа экономики»
Эмоции и темы публичного дискурса об ИИ
Анна Чижик
Университет ИТМО

← Session 1 - English track (24 June, 10:00–11:30, Room 1222) →

TL;DR: Text Normalization for Social Media Corpus
Grigorii Feoktistov, Dmitry Morozov
Novosibirsk State University, Russian National Corpus
Russian Neural Morpheme Segmentation: From Lemmata to Wordforms
Dmitry Morozov, Olga Shcherbakova, Anna Glazkova
Novosibirsk State University, University of Tyumen, Russian National Corpus
An Experimental Study of Automating Explanatory Dictionary Compilation with Language Models
Timur Garipov, Dmitry Morozov, Yana Gubarkova, Anastasia Kozerenko, Anna Glazkova
Novosibirsk State University, Yandex LLC, V.V. Vinogradov Russian Language Institute RAS, University of Tyumen, Russian National Corpus
Word Sense Disambiguation in Russian: A Generative LLM Approach
Polina Gousyatskaya, Natalia Loukachevitch
Lomonosov Moscow State University
Modelling Arabic Toponym Transliteration into English and Russian
Sofia Shevtsovа
National Research University Higher School of Economics

← Session 2 - English track (24 June, 12:00–13:30, Room 1222) →

Mapping Effective Teaching with Topic Modeling
Ivan Mamaev
Saint Petersburg State University, Baltic State Technical University “Voenmeh” named after D.F. Ustinov
What Officials Talk About? Uncovering Themes and Trends in Interviews with Russian Officials Through Topic Modeling
Sofiia Chepovetskaia
National Research University Higher School of Economics, Saint-Petersburg State University
Profiling the corpus of tutor advertising texts: a statistical and linguistic analysis
Nadezhda Ogorodova
Baltic State Technical University “VOENMEH” named after D.F. Ustinov
Creating a dataset for automatic detection of vague expressions in Russian legal texts
Olga Blinova, Alyona Berlin
National Research University Higher School of Economics, Saint-Petersburg State University
Five-Minute Reads: Exploring the Factors that Influence Automatic Summarization of Literary Texts
Alisa Lukyanchikova, Margarita Kirina
National Research University Higher School of Economics
The Influence of Language Typological Features on Neural Summarization Performance
Mark Athugodage, Olga Mitrofanova
National Research University Higher School of Economics, Saint-Petersburg State University

← Session 3 - English track (24 June, 14:30–16:00, Room 1222) →

Optimising Terminology Processing in Unmanned Aviation: a New Approach to Term Extraction Using Prompt Engineering
Ekaterina Isaeva, Behruz Safarbekov
Perm State University, National University of Science and Technology MISiS
Dialog Flow Analytics Toolkit for a Contact Center Platform
Alena Zhivotova, Valeria Zarembo
Erllecta LLC
Measuring Public Satisfaction with Service Quality: customer-oriented approach
Svetlana Sheremetyeva, Olga Babina, Andrew Polev
South Ural State University
Emotion-Sentiment Profiling of Customer Feedback through Cluster-Driven Analysis
Olga Babina, Svetlana Sheremetyeva
South Ural State University
Do LLMs Understand Why We Write Diaries? A Method for Purpose Extraction and Clustering
Valeriya Goloviznina, Alexander Sergeev, Mikhail Melnichenko, Evgeny Kotelnikov
European University at Saint Petersburg

← Prev Session ↔ Next Session →

Mission of the Seminar

Bridging the worlds of computational linguistics, corpus linguistics, and modern AI methods like machine learning and NLP, the seminar fosters innovation, collaboration, and a deeper understanding of language and algorithms working together.
The main gathering takes place in June within the framework of the international conference Internet and Modern Society (IMS–2025), St. Petersburg, Russia, complemented by three key meetups throughout the year: on large language models, text mining, and Zakharov Day (March).
Our target audience includes linguists, data scientists, and industry professionals working with language processing and understanding technologies.

Zakharov.Day

The Zakharov.Day meetup took place online on March 13, 2025. It featured keynote presentations by Margarita Kirina (HSE) on emotions in digital literature research and Olga Mitrofanova (SPbU) on building text corpora.

The program also included lightning talks showcasing early-stage research.


You can now watch the keynote presentations from Zakharov.Day.

🎥 Watch Recording

Contact Us

Have questions or need more information about the seminar? Reach out to us using the form below, and we’ll get back to you shortly.