All issues

We offer the dissipative stochastic dynamic model of the language sign evolution, satisfying to the principle of the least action, one of fundamental variational principles of the Nature. The model conjectures the Poisson nature of the birth flow of language signs and the exponential distribution of their associative-semantic potential (ASP). The model works with stochastic difference equations of the special type for dissipative processes. The equation for momentary polysemy distribution and frequency-rank distribution drawn from our model do not differs significantly (by Kolmogorov-Smirnov’s test) from empirical distributions, got from main Russian and English explanatory dictionaries as well as frequency dictionaries of them.

The paper contains the analysis of the domestic publications issued in 2013–2017 years and devoted to cellular automata. The most of them concern on mathematical modeling. Scientometric schedules for 1990–2017 years have proved relevance of subject. The review allows to allocate the main personalities and the scientific directions/schools in modern Russian science, to reveal their originality or secondness in comparison with world science. Due to the authors choice of national publications basis instead of world, the paper claims the completeness and the fact is that about 200 items from the checked 526 references have an importance for science.

In the Annex to the review provides preliminary information about CA — the Game of Life, a theorem about gardens of Eden, elementary CAs (together with the diagram of de Brujin), block Margolus’s CAs, alternating CAs. Attention is paid to three important for modeling semantic traditions of von Neumann, Zuse and Zetlin, as well as to the relationship with the concepts of neural networks and Petri nets. It is allocated conditional 10 works, which should be familiar to any specialist in CA. Some important works of the 1990s and later are listed in the Introduction.

Then the crowd of publications is divided into categories: the modification of the CA and other network models (29 %), Mathematical properties of the CA and the connection with mathematics (5 %), Hardware implementation (3 %), Software implementation (5 %), Data Processing, recognition and Cryptography (8 %), Mechanics, physics and chemistry (20 %), Biology, ecology and medicine (15 %), Economics, urban studies and sociology (15 %). In parentheses the share of subjects in the array are indicated. There is an increase in publications on CA in the humanitarian sphere, as well as the emergence of hybrid approaches, leading away from the classic CA definition.

Intent detection plays a crucial role in task-oriented conversational systems. To understand the user’s goal, the system relies on its intent detector to classify the user’s utterance, which may be expressed in different forms of natural language, into intent classes. However, lack of data, and the efficacy of intent detection systems has been hindered by the fact that the user’s intent text is typically characterized by short, general sentences and colloquial expressions. The process of algorithmically determining user intent from a given statement is known as intent detection. The goal of this study is to develop an intent detection model that will accurately classify and detect user intent. The model calculates the similarity score of the three models used to determine their similarities. The proposed model uses Contextual Semantic Search (CSS) capabilities for semantic search, Latent Dirichlet Allocation (LDA) for topic modeling, the Bidirectional Encoder Representations from Transformers (BERT) semantic matching technique, and the combination of LDA and BERT for text classification and detection. The dataset acquired is from the broad twitter corpus (BTC) and comprises various meta data. To prepare the data for analysis, a pre-processing step was applied. A sample of 1432 instances were selected out of the 5000 available datasets because manual annotation is required and could be time-consuming. To compare the performance of the model with the existing model, the similarity scores, precision, recall, f1 score, and accuracy were computed. The results revealed that LDA-BERT achieved an accuracy of 95.88% for intent detection, BERT with an accuracy of 93.84%, and LDA with an accuracy of 92.23%. This shows that LDA-BERT performs better than other models. It is hoped that the novel model will aid in ensuring information security and social media intelligence. For future work, an unsupervised LDA-BERT without any labeled data can be studied with the model.

We propose a generalized probabilistic topic model of text corpora which can incorporate heuristics of Bayesian regularization, sampling, frequent parameters update, and robustness in any combinations. Wellknown models PLSA, LDA, CVB0, SWB, and many others can be considered as special cases of the proposed broad family of models. We propose the robust PLSA model and show that it is more sparse and performs better that regularized models like LDA.

Interpretability in recent deep learning models has become an epicenter of research particularly in sensitive domains such as healthcare, and finance. Concept bottleneck models have emerged as a promising approach for achieving transparency and interpretability by leveraging a set of humanunderstandable concepts as an intermediate representation before the prediction layer. However, manual concept annotation is discouraged due to the time and effort involved. Our work explores the potential of large language models (LLMs) for generating high-quality concept banks and proposes a multimodal evaluation metric to assess the quality of generated concepts. We investigate three key research questions: the ability of LLMs to generate concept banks comparable to existing knowledge bases like ConceptNet, the sufficiency of unimodal text-based semantic similarity for evaluating concept-class label associations, and the effectiveness of multimodal information in quantifying concept generation quality compared to unimodal concept-label semantic similarity. Our findings reveal that multimodal models outperform unimodal approaches in capturing concept-class label similarity. Furthermore, our generated concepts for the CIFAR-10 and CIFAR-100 datasets surpass those obtained from ConceptNet and the baseline comparison, demonstrating the standalone capability of LLMs in generating highquality concepts. Being able to automatically generate and evaluate high-quality concepts will enable researchers to quickly adapt and iterate to a newer dataset with little to no effort before they can feed that into concept bottleneck models.

Events and character extraction from narratives is a fundamental task in text analysis. The application of event extraction techniques ranges from the summarization of different documents to the analysis of medical notes. We identify events based on a framework named “four W” (Who, What, When, Where) to capture all the essential components like the actors, actions, time, and places. In this paper, we explore two prominent techniques for event extraction: statistical parsing of syntactic trees and semantic role labeling. While these techniques were investigated by different researchers in isolation, we directly compare the performance of the two approaches on our custom dataset, which we have annotated.

Our analysis shows that statistical parsing of syntactic trees outperforms semantic role labeling in event and character extraction, especially in identifying specific details. Nevertheless, semantic role labeling demonstrate good performance in correct actor identification. We evaluate the effectiveness of both approaches by comparing different metrics like precision, recall, and F1-scores, thus, demonstrating their respective advantages and limitations.

Moreover, as a part of our work, we propose different future applications of event extraction techniques that we plan to investigate. The areas where we want to apply these techniques include code analysis and source code authorship attribution. We consider using event extraction to retrieve key code elements as variable assignments and function calls, which can further help us to analyze the behavior of programs and identify the project’s contributors. Our work provides novel understandings of the performance and efficiency of statistical parsing and semantic role labeling techniques, offering researchers new directions for the application of these techniques.

This paper investigates the effectiveness of Retrieval-Augmented Generation (RAG) combined with various Large Language Models (LLMs) for document retrieval and information access in corporate information systems. We survey typical use-cases of LLMs in enterprise environments, outline the RAG architecture, and discuss the major challenges that arise when integrating LLMs into a RAG pipeline. A system architecture is proposed that couples a text-vector encoder with an LLM. The encoder builds a vector database that indexes a library of corporate documents. For every user query, relevant contextual fragments are retrieved from this library via the FAISS engine and appended to the prompt given to the LLM. The LLM then generates an answer grounded in the supplied context. The overall structure and workflow of the proposed RAG solution are described in detail. To justify the choice of the generative component, we benchmark a set of widely used LLMs — ChatGPT, GigaChat, YandexGPT, Llama, Mistral, Qwen, and others — when employed as the answer-generation module. Using an expert-annotated test set of queries, we evaluate the accuracy, completeness, linguistic quality, and conciseness of the responses. Model-specific characteristics and average response latencies are analysed; the study highlights the significant influence of available GPU memory on the throughput of local LLM deployments. An overall ranking of the models is derived from an aggregated quality metric. The results confirm that the proposed RAG architecture provides efficient document retrieval and information delivery in corporate environments. Future research directions include richer context augmentation techniques and a transition toward agent-based LLM architectures. The paper concludes with practical recommendations on selecting an optimal RAG–LLM configuration to ensure fast and precise access to enterprise knowledge assets.

WS-BPEL is a widely accepted standard for specification of business distributed and parallel processes. This standard is a mismatch of algebraic and Petri net paradigms. Following that, it is easy to specify WS-BPEL business process with unwanted features. That is why the verification of WS-BPEL business processes is very important. The intent of this paper is to show some possibilities for conversion of a WS-BPEL processes into more formal specifications that can be verified. CSP and Z-notation are used as formal models. Z-notation is useful for specification of abstract data types. Web services can be viewed as a kind of abstract data types.

In our research, we focus on the problem of classification for silent speech recognition to develop a brain– computer interface (BCI) based on electroencephalographic (EEG) data, which will be capable of assisting people with mental and physical disabilities and expanding human capabilities in everyday life. Our previous research has shown that the silent pronouncing of some words results in almost identical distributions of electroencephalographic signal data. Such a phenomenon has a suppressive impact on the quality of neural network model behavior. This paper proposes a data processing technique that distinguishes between statistically remote and inseparable classes in the dataset. Applying the proposed approach helps us reach the goal of maximizing the semantic load of the dictionary used in BCI.

Furthermore, we propose the existence of a statistical predictive criterion for the accuracy of binary classification of the words in a dictionary. Such a criterion aims to estimate the lower and the upper bounds of classifiers’ behavior only by measuring quantitative statistical properties of the data (in particular, using the Kolmogorov – Smirnov method). We show that higher levels of classification accuracy can be achieved by means of applying the proposed predictive criterion, making it possible to form an optimized dictionary in terms of semantic load for the EEG-based BCIs. Furthermore, using such a dictionary as a training dataset for classification problems grants the statistical remoteness of the classes by taking into account the semantic and phonetic properties of the corresponding words and improves the classification behavior of silent speech recognition models.