Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Volodymyr Shymkovych has a total of 38 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Controlled Evaluation of Document-Level Inter-Mention Links for Named-Entity Type Classification in Ukrainian Texts

    by Oleksii Hryshyn, Volodymyr Shymkovych, Damian Grela

    Document-level links between repeated mentions can provide contextual evidence unavailable to a local entity-type classifier, a potentially important capability for Ukrainian because of its limited annotated resources and rich inflectional morphology. However, their specific contribution is difficult to isolate because graph-based systems often simultaneously alter the classifier architecture. We evaluate named-entity type classification with known mention boundaries on NER-UK 2.0 under controlled conditions, using frozen XLM-RoBERTa-base representations, 10 optimization seeds, and 270 graph-head training runs. The evaluation design combines a no-message baseline with matched head parameterization, degree-preserving topology shuffling, simple averaging, oracle diagnostics, and controlled context-weakening interventions; no novel graph architecture is claimed. On intervention-free data, the exact-repeat graph changed macro-F1 by +0.0041 (95% CI [−0.0042,0.0127]); thus, an overall benefit was not established, although the interval did not rule out a practically meaningful effect. A Ukrainian token-level lemmatization rule increased graph coverage from 34.41% to 42.07% but did not improve performance over exact repetition (Δ=−0.0033, 95% CI [−0.0135,0.0055]). When only the target mention’s context was artificially weakened, with no explicit degradation cue, graph refinement increased target accuracy by 0.0784 (95% CI [0.0544,0.1021]). The advantage reversed when the entire repeat component was weakened, while simple averaging performed at least as well as the learned graph head. Overall, the results support graph-based refinement as a conditional context-recovery mechanism rather than a universal replacement for local classification. The evidence remains controlled but not independently confirmatory and does not establish gains for end-to-end NER or robustness to naturally degraded context.

  • Open Access

    Information System for Bank Portfolio Credit Risk Analysis Based on a Three-tier Data Warehouse Architecture

    by Volodymyr Shymkovych, Pavlo Minin

    This paper proposes an information system for bank portfolio credit risk analysis based on a three-tier data warehouse architecture. The proposed solution integrates a centralized data warehouse, online analytical processing, a modular data import subsystem, and a Business Intelligence platform to support automated data integration, analytical processing, visualization, and reporting. A three-tier data warehouse model with subject-oriented data marts is developed to improve data organization and analytical performance. The architecture of the data import module is designed using a clear separation of responsibilities between software components, providing modularity, scalability, and maintainability. The analytical capabilities of the developed system are demonstrated through regression analysis of non-performing loans, confirming its applicability for automated portfolio credit risk assessment and decision support.

  • Open Access

    A Unified Neural Framework for Punctuation and Capitalization Restoration Using XLM-RoBERTa–BiLSTM

    by Volodymyr Shymkovych, Grzegorz Nowakowski, Sergii Telenyk, Artem Kramov

    Accurate punctuation and capitalization are essential for the readability, interpretability, and structural coherence of machine-generated text. Their absence is particularly problematic in automatic speech recognition outputs and other forms of unstructured text, where missing punctuation and incorrect capitalization reduce both human readability and the effectiveness of downstream natural language processing tasks. This study proposes a hybrid XLM-RoBERTa–BiLSTM model for joint punctuation restoration and text capitalization on English-language data. The proposed architecture combines contextual representations produced by the multilingual pre-trained XLM-RoBERTa encoder with the sequential modeling capabilities of a bidirectional long short-term memory layer, followed by token-level classification in a unified label space. The model was trained and evaluated on a dataset derived from the IWSLT 2012 TED Talks corpus. Experimental evaluation on a held-out random test subset demonstrates strong performance. Excluding the dominant no-punctuation class, the model achieves an accuracy of 0.929, precision of 0.892, recall of 0.914, and an F1-score of 0.903. Including the dominant no-punctuation class increases these values to 0.961, 0.927, 0.919, and 0.923, respectively, reflecting the pronounced class imbalance in the dataset. Class-wise analysis shows high effectiveness for frequent punctuation classes and reliable capitalization prediction, whereas rare punctuation–capitalization categories remain more challenging because of their limited representation in the training and test subsets. Overall, the proposed hybrid XLM-RoBERTa–BiLSTM architecture achieves strong performance in joint punctuation restoration and text capitalization and represents an effective approach to improving the readability and structural quality of automatic speech recognition transcripts and other machine-generated text.

  • Mathematical models of software components for infocommunication service providers

    by D.O. Vitkovskyi, V.M. Shymkovych

    The automation of solving intellectual tasks—specifically, the design of software components for information and communication service providers—using artificial intelligence is an important and timely issue in service lifecycle management platforms for IT development companies based on the End-to-End model. This paper addresses the problem of synthesizing service component code using deep learning models. The requirements for service components are analyzed, and possible service component codes are examined. A mathematical model has been developed to describe the requirements for service software components. The paper analyzes existing mathematical models for representing program code in the Java language that can be used for the mathematical description of service component code. A mathematical model of the program code of service components has been developed, which differs from existing ones in control and adaptation to the features of the grammar of a specific language. This allows for the continued use of unimodal language models. The proposed model is a component of the platform for supporting the life cycle of services in information systems of providers. Within an integrated system of tools for automating service lifecycle processes, the proposed mathematical models will enable the training and implementation of deep neural networks for designing the program code of service components.

  • FPGA-Based Method for Automated Design of Neural Network Controllers

    by V. M. Shymkovych, A. Yu. Doroshenko, P. I. Kravets, O. A. Yatsenko

  • Open Access

    A Multimodal Retrieval-Augmented Generation System with ReAct Agent Logic for Multi-Hop Reasoning

    by Denys Yuvzhenko, Viacheslaw Chymshyr, Volodymyr Shymkovych, Kyrylo Znova, Grzegorz Nowakowski, Sergii Telenyk

    The rapid advancement of generative artificial intelligence models significantly influences modern methods of information processing and user interactions with information systems. One of the promising areas in this domain is Retrieval-Augmented Generation (RAG), which combines generative models with information retrieval methods to enhance the accuracy and relevance of responses. However, most existing RAG systems primarily focus on textual data, which does not meet contemporary needs for multimodal information processing (text, images, tables). The research object of this work is a multimodal RAG system based on ReAct agent logic, capable of multi-hop reasoning. The main emphasis is placed on integrating textual, graphical, and tabular information to generate accurate, complete, and relevant responses. The system's implementation utilized the ChromaDB vector storage, the OpenAI embedding generation model (text-embedding-ada-002), and the GPT-4 language model. The purpose of the study is the development, deployment, and empirical evaluation of the proposed multimodal RAG system based on the ReAct agent approach, capable of effectively integrating diverse knowledge sources into a unified informational context. The experimental evaluation utilized the Global Tuberculosis Report 2024 by the World Health Organization, containing various textual, graphical, and tabular data. A specialized test set of 50 queries (30 textual, 10 tabular, 10 graphical) was created for empirical analysis, allowing comprehensive testing of all aspects of multimodal integration. The research employed methods such as semantic vector search, multi-hop agent-based planning with ReAct logic, and evaluations of answer accuracy, answer recall, and response latency. Additionally, an analysis of response speed dependence on query volume was conducted. The obtained results confirmed the high efficiency of the proposed approach. The system demonstrated an answer accuracy of 92%, answer recall of 89%, and ensured complete (100%) coverage of all data types. The average response time was approximately 5 seconds, meeting interactive system requirements. Optimal parameters were experimentally determined (for example, parameter k = 6, classification threshold 0.35, and up to three reasoning iterations), ensuring the best balance among completeness, speed, and operational efficiency. The study's findings highlighted significant advantages of the multimodal agent-based approach compared to traditional textual RAG solutions, confirming the promising direction for further research.


  • Open Access

    Scientific article summarization model with unbounded input length

    by Oleksandr Steblianko, Volodymyr Shymkovych, Peter Kravets, Anatolii Novatskyi, Lyubov Shymkovych

    In recent years, the exponential growth of scientific literature has made it increasingly difficult for researchers and practitioners to keep up with new discoveries and developments in their fields. Thanks to this, text summarization has become one of the primary tasks of natural language processing. Abstractive summarization of long documents, such as scientific articles, requires large neural networks with high memory and computation requirements. Therefore, it is all the more important to find ways to increase the efficiency of long document summarization models. The objects of this research are long document summarization transformer models and the Unlimiformer cross-attention modification. The article reviews the basic principles of transformer attention, which constitutes the primary computational expense in transformer models. More efficient self-attention approaches used for long document summarization models are described, such as the global+sliding window attention used by Longformer. The cross-attention mechanism of Unlimiformer, which allows a model to have unbounded input length, is described in detail. The objective of the study is the development and evaluation of a long document summarization model using the Unlimiformer modification. To achieve this goal, a Longformer Decoder-Encoder model pretrained on the arXiv dataset is modified with Unlimiformer cross-attention. This modification can be applied without additional model fine-tuning, avoiding the cost of further training a large sequence length model. The developed model was evaluated on the arXiv dataset using the ROUGE-1, ROUGE-2 and ROUGE-L metrics. The developed model showed improved results compared to the baseline model, demonstrating the viability of using this approach to improve long document summarization models.


  • Open Access

    An intelligent chatbot for evaluating the emotional colouring of a message and responding accordingly

    by Ntuu, V. R. Kobchenko, Kpi, V.M. Shymkovysh, Ntuu Kpi, P.I. Kravets, A.O. Novatskyi, L.L. Shymkovysh, А.YU. Doroshenko

    A recurrent neural network model, a database designed for neural network training, and a software tool for interacting with a bot have all been created. A large dataset (50 thousand comments) containing different reviews and sentiments was collected and annotated to successfully train and validate the model. It was also translated into Ukrainian language with the help of an automatic translator. The architecture of the neural network model underwent optimization to enhance classification outcomes. Furthermore, work was conducted on enhancing the user interface. The developed application was tested, and the results were demonstrated. The resulting model demonstrated accuracy 85% in determining sentiments. The implemented application has got basic design (which can be customized) and some settings for chatbot. Further improvement of the model’s classification quality can be achieved by collecting a larger and better organised dataset or by researching other RNN architectures.


  • Neural Network Model for Laboratory Stand Control System Controller with Parallel Mechanisms

    by Peter Kravets, Anatolii Novatskyi, Volodymyr Shymkovych, Antonina Rudakova, Yurii Lebedenko, Hanna Rudakova