arXiv subjects

Ivan Polasek

Publications and source records attributed to Ivan Polasek.

5 recordsLinked to original sources

arXiv2026

Approaches to Semantic Textual Similarity in Slovak Language: From Algorithms to Transformers

Semantic textual similarity (STS) plays a crucial role in many natural language processing tasks. While extensively studied in high-resource languages, STS remains challenging for under-resourced languages such as Slovak. This paper presents a comparative evaluation of sentence-level STS methods applied to Slovak, including traditional algorithms, supervised machine learning models, and third-party deep learning tools. We trained several machine learning models using outputs from traditional algorithms as features, with feature selection and hyperparameter tuning jointly guided by artificial bee colony optimization. Finally, we evaluated several third-party tools, including fine-tuned model by CloudNLP, OpenAI's embedding models, GPT-4 model, and pretrained SlovakBERT model. Our findings highlight the trade-offs between different approaches.

cs.CL↗

arXiv2026

Supporting software engineering tasks with agentic AI: Demonstration on document retrieval and test scenario generation

The introduction of large language models ignited great retooling and rethinking of the software development models. The ensuing response of software engineering research yielded a massive body of tools and approaches. In this paper, we join the hassle by introducing agentic AI solutions for two tasks. First, we developed a solution for automatic test scenario generation from a detailed requirements description. This approach relies on specialized worker agents forming a star topology with the supervisor agent in the middle. We demonstrate its capabilities on a real-world example. Second, we developed an agentic AI solution for the document retrieval task in the context of software engineering documents. Our solution enables performing various use cases on a body of documents related to the development of a single software, including search, question answering, tracking changes, and large document summarization. In this case, each use case is handled by a dedicated LLM-based agent, which performs all subtasks related to the corresponding use case. We conclude by hinting at the future perspectives of our line of research.

cs.SE↗

arXiv2026

Large Language Models in Software Documentation and Modeling: A Literature Review and Findings

Generative artificial intelligence attracts significant attention, especially with the introduction of large language models. Its capabilities are being exploited to solve various software engineering tasks. Thanks to their ability to understand natural language and generate natural language responses, large language models are great for processing various software documentation artifacts. At the same time, large language models excel at understanding structured languages, having the potential for working with software programs and models. We conduct a literature review on the usage of large language models for software engineering tasks related to documentation and modeling. We analyze articles from four major venues in the area, organize them per tasks they solve, and provide an overview of used prompt techniques, metrics, approaches to human-based evaluation, and major datasets.

cs.SE↗

arXiv2025

Executable Multi-Layered Software

This paper introduces a novel software visualisation and animation method, manifested in a prototype software tool - AnimArch. The introduced method is based on model fusion of static and dynamic models. The static model is represented by class diagram while the dynamic model is represented by source code written in high-level Object Action Language from xUML (executable UML). The class diagram defines architecture that is animated in response to real-time execution of the source code. Moreover, additional object diagram layer represents all object instances present in runtime. The AnimArch also features source code generation to Python, to bridge the gap from design to implementation. This paper provides detailed description of the modelling method and screenshots of the accompanying software tool.

cs.SE↗

arXiv2023

Collaborative software design and modeling in virtual reality

Context: Software engineering is becoming more and more distributed. Developers and other stakeholders are often located in different locations, departments, and countries and operating within different time zones. Most online software design and modeling tools are not adequate for distributed collaboration since they do not support awareness and lack features for effective communication. Objective: The aim of our research is to support distributed software design activities in Virtual Reality (VR). Method: Using design science research methodology, we design and evaluate a tool for collaborative design in VR. We evaluate the collaboration efficiency and recall of design information when using the VR software design environment compared to a non-VR software design environment. Moreover, we collect the perceptions and preferences of users to explore the opportunities and challenges that were incurred by using the VR software design environment. Results: We find that there is no significant difference in the efficiency and recall of design information when using the VR compared to the non-VR environment. Furthermore, we find that developers are more satisfied with collaboration in VR. Conclusion: The results of our research and similar studies show that working in VR is not yet faster or more efficient than working on standard desktops. It is very important to improve the interface in VR (gestures with haptics, keyboard and voice input), as confirmed by the difference in results between the first and second evaluation.

cs.SE↗