?
РАЗРАБОТКА DSM-ПЛАТФОРМЫ: СРЕДСТВА ТРАНСФОРМАЦИИ МОДЕЛЕЙ ВИДА «МОДЕЛЬ-ТЕКСТ»
С. 124–134.
Проскуряков К. А., Lyadova L. N.
The goal of the study is to approval the approach to creating tools for generating code from visual models for a DSM platform based on knowledge and metamodeling. The basis of the solution is a multifaceted ontology, describing languages, designed to solve various tasks of designing and analysing systems, and the domains in which users solve these tasks. Code generation is implemented based on transformation rules that users develop using the constructor. The ontology structure and the transformation module structure, the application user interface and examples of languages and transformation rules representing in the ontology are described.
Keywords: метамоделированиепредметно-ориентированные языкиmetamodelingпредметно-ориентированное моделированиеDSM-платформаDSLтрансформация моделейmodel transformationsdomain specific modelingDSLDSM platformcode generationгенерация кодаmultifaceted ontologyмногоаспектная онтологияdomain specific languages
In book
Таганрог: Издательство ЮФУ, 2023.
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
Джейранян А. Д., Ларионова Я. А., Lyadova L. N., В кн.: ГрафиКон 2025 : материалы 35-й Международной конференции по компьютерной графике и машинному зрению (Россия, Йошкар-Ола, 30 сентября – 2 октября 2025 г.).: Йошкар-Ола: Поволжский государственный технологический университет, 2025. С. 353–366.
Abstract. Data visualization tools are key analytics tools that make it easier to identify dependencies, trends, and patterns. These tools are used by a broad range of specialists (analysts, scientists, business leaders, managers, teachers, and specialists in other fields where accurate and understandable presentation of information is critically important to improve the effectiveness of data ...
Added: May 5, 2026
Джейранян А. Д., Ларионова Я. А., Lyadova L. N., В кн.: ГрафиКон 2025 : материалы 35-й Международной конференции по компьютерной графике и машинному зрению (Россия, Йошкар-Ола, 30 сентября – 2 октября 2025 г.).: Йошкар-Ола: Поволжский государственный технологический университет, 2025. С. 353–366.
Data visualization tools are key analytics tools that make it easier to identify dependencies, trends, and patterns. These tools are used by a broad range of specialists (analysts, scientists, business leaders, managers, teachers, and specialists in other fields where accurate and understandable presentation of information is critically important to improve the effectiveness of data analysis). ...
Added: February 21, 2026
Джейранян А. Д., Lyadova L. N., В кн.: BIG DATA и анализ высокого уровня = BIG DATA and Advanced Analytics: сб. науч. ст. XI Междунар. науч.-практ. конф. (Республика Беларусь, Минск, 23–24 апреля 2025 года).: Мн.: БГУИР, 2025. С. 386–396.
An analysis of existing data visualization methods and tools was conducted, revealing their limitations associated with the need for advanced programming skills or insufficient configuration flexibility. A methodology for developing data visualization tools based on expert knowledge is proposed, enabling the effective creation of customizable visual representations. The methodology comprises three key approaches: (1) the ...
Added: February 21, 2026
Vasilevsky V., Alexandrov D., Proceedings of the Institute for System Programming of the RAS 2025 Vol. 37 No. 5 P. 173–182
Automatic code generation by large language models (LLMs) has achieved significant success, yet
it still faces challenges when dealing with complex and large codebases, especially in languages like Java. The
limitations of LLM context windows and the complexity of debugging generated code are key obstacles. This
paper presents an approach aimed at improving Java code generation and debugging. ...
Added: December 26, 2025
Integrating an Ontology-Driven Approach to Data Visualization and AI Based Visualization with Plotly
A.D. Dzheiranian, L.N. Lyadova, Proceedings of the Institute for System Programming of the RAS 2025 Vol. 37 No. 4 P. 191–206
This study introduces an AI-driven assistant prototype that automates the generation of data visualization scripts from natural language queries, eliminating the need for users to have programming skills. The article examines research aimed at developing tools for effective data visualization, compares data visualization systems based on the use of artificial intelligence, and shows the limitations ...
Added: September 25, 2025
Lyudmila Lyadova, Anton Platunov, Lanin V. et al., , in: Knowledge Discovery, Knowledge Engineering and Knowledge Management: 15th International Joint Conference, IC3K 2023, Rome, Italy, November 13-15, 2023, Revised Selected PapersVol. 2454.: Rome: Springer, 2025. Ch. 11 P. 232–250.
Existing process mining methods based on analysing event logs containing mandatory event attributes allow to investigate processes in different domains. Additional attributes extending mandatory set of values can be presented in various data sources. Domain experts need to analyse dynamics of changing the values of additional attributes to get important information on events and to ...
Added: May 2, 2025
Ebraheem A., Ivanov I., , in: 2024 International Russian Automation Conference (RusAutoCon).: IEEE, 2024. P. 1012–1016.
Designing reliable Internet of Things systems requires careful planning and consideration of different factors. Incorporating multi-objective optimization methods may help achieve this goal. In this article, a domain-specific language is proposed to aid in describing the structure of the Internet of Things and formulating the requirements and objectives in a simple context. The code is ...
Added: January 9, 2025
Резуник Л., Александров Д.В., ИТ-Стандарт 2024 № 4 С. 34–41
Machine learning technologies and various tools for code generation have had a significant impact on the field of software development in recent years. Although most of the existing solutions are not built exactly for code generation, programmers apply them in different tasks. Not many of the existing AI solutions work well with less common languages, ...
Added: December 30, 2024
Проскуряков К. А., Lyadova L. N., В кн.: Технологии разработки инструментальных средств (ТРИС-2024) : Материалы XIV Международной научно-технической конференции.: Таганрог: Издательство ЮФУ, 2024. С. 207–219.
Abstract: The goal of the project is to approve an approach to generating code implementing user data visualization models based on metamodels of visual domain-specific languages (DSL), created to describe visualization models, and descriptions of formal grammars of target textual programming languages presented in a multi-aspect ontology. The ontology also includes descriptions of “Model-Text” transformation ...
Added: December 11, 2024