Abstract:

The article addresses the problem of communicative bias in automatic speech recognition systems when processing atypical speech in Russian. The relevance of the study is driven by the active integration of artificial intelligence technologies into the social sphere and public administration in Russia, which presupposes ensuring their accessibility for various categories of citizens, including people with speech disorders. The authors introduce the concept of communicative bias of ASR models as a property of a system that, under conditions of uncertainty (atypical speech, noise, pauses), makes decisions about filling semantic and acoustic gaps based on its own training data rather than the speaker's actual communicative intention. The empirical basis of the study is the RuAphasiaBank corpus, which includes speech recordings from patients with various types of aphasia of varying severity, as well as neurotypical informants. For comparative analysis, six ASR models operating with Russian were selected: two open-source (GigaAM, T-One) and four commercial (Yandex SpeechKit, Any2Text, Charla, Speech2Text). Recognition quality was assessed using WER and CER metrics, as well as a qualitative analysis of the ratio of insertions, deletions, and substitutions at the word and character levels. The results show that the models implement different strategies when encountering atypical speech: “panic shortening” (GigaAM, Yandex SpeechKit), “lexical preservation” at the expense of accuracy (T-One), and a “stable” strategy of balanced errors (Any2Text, Speech2Text, Charla). Linguistic analysis reveals that each model produces a specific distorted communicative style, ranging from colloquial dialogic speech to a style associated with cognitive impairments or the use of youth slang. Based on the obtained data, potential risks to the social well-being and legal security of aphasia patients when using voice assistants in public institutions are modeled.

Abstract:

Translated plagiarism has widely spread in a scientific world and posed a serious problem due to the challenges in its automatic detection. However, in the last five years some progress has been observed in this area. The authors of this paper, as well as foreign research team from several universities independently of each other proposed an approach to detect plagiarism based on citation analysis with search of initial source for analyzed suspected paper with the same or similar references. Developed methods of detection of illegal use of borrowed text successfully passed several tests. The report shows the results that we have obtained in the last four years.

Abstract:

The design of curricula in the context of the dynamics of educational standards is shifting from a static set of disciplines to system modeling. This approach should take into account multilevel relationships and the logic of forming cross–cutting competencies. The purpose of the research is to create and test methodological tools for the analysis of educational programs of universities based on network analysis methods. The curriculum is formalized in the form of an undirected graph, where the vertices are disciplines, and the edges are connections through common competencies. The work uses a multidimensional network analysis, including the calculation of centrality measures (degree, betweenness, closeness, eigenvector) and key topological metrics: density, modularity, diameter, and clustering coefficient. The empirical base was made up of data from the curricula of three universities in Omsk. The analysis revealed significant structural and topological differences in the architecture of educational programs due to their departmental affiliation and target training models. Network metrics make it possible to quantify the interdisciplinary connectivity and modularity of programs, which is not available for traditional approaches. The results obtained confirm the high diagnostic potential of network analysis for sound optimization of curricula and verification of compliance with professional competencies.

Abstract:

The rapid increase in the volume of publications in various fields of geology makes it crucial to introduce methods for automated processing of scientific texts. Large language models based on neural networks represent one of the most promising approaches to solving this challenge. The recent breakthroughs in artificial intelligence have made such models indispensable tools for researchers. Our work on semantic search for publications using additionally trained language models and measuring the similarity between geological texts yielded good results. However, the models we used were unable to perform in-depth text analysis. A comparative analysis of modern architectures identified the DeepSeek R1 model as belonging to a class of systems with advanced logical inference abilities. This type of model represents a fundamentally new level of quality in text generation. Based on the chosen model, we have developed a web service that provides unique functionality for comparative analysis of up to 5 scientific articles. The service supports multilingual sources, allowing users to input text in English, Chinese, Russian, etc. It generates structured reports in Russian, highlighting key theses, contradictions, and patterns. The proposed approach has been tested on geological publications, and the results have been promising.

Abstract:

Modern scientometric systems and citation systems use various mechanisms of thematic search and thematic filtering of information. In most cases, a full-text approach is used for thematic analysis of articles and journals, which has a number of limitations. The use of algorithms based on graph analysis, both independently and in conjunction with full-text algorithms, eliminates these limitations and improves the completeness and accuracy of subject search. The algorithm developed by the authors and presented in this work uses the co-authorship graph to analyze the thematic proximity of journals. The algorithm is insensitive to the language of the journal and selects similar journals in different languages, which is difficult to implement for algorithms based on the analysis of full-text information. The algorithm was tested in the scientometric system IAS ISTINA. In the interface developed for these purposes, the user can select one journal that is close to him on the subject, and the system will automatically generate a selection of journals that may be of interest to the user both in terms of studying the materials available in them and in terms of publishing his own articles. In the future, the developed algorithm can be adapted to search for similar conferences, collections of publications and scientific projects. The presence of such a tool will increase the publication activity of young employees, increase the citation rate of articles and the citation rate between journals. The results of the algorithm for determining thematic proximity between journals, collections, conferences and scientific projects can also be used to build rules in models of differentiating access to data based on domain ontologies.

Abstract:

The paper assesses the limits of applicability of large language models in editorial tasks within the publishing process and identifies the optimal format of interaction between humans and algorithmic systems.

The methodological basis of the study is a comparative experiment in which several popular neural network models — Alice AI, GigaChat, DeepSeek, Gemini, and ChatGPT — performed a statistical analysis of a control text in Russian. The quantitative characteristics of the text were determined: the number of words, characters with and without spaces, and the number of paragraphs. The obtained results were compared with reference values established using the MS Word text editor, which applies a deterministic character-counting algorithm.

The results of the experiment showed that neural network models demonstrate varying degrees of accuracy when performing tasks of quantitative text analysis. The main reason for such errors lies in the architecture of large language models and the use of tokenization algorithms, which break the direct connection between characters and the model’s internal representation of the text.

Based on the results obtained, the paper proposes the concept of a hybrid architecture for publishing information systems, in which generative language models are used to perform creative and analytical tasks, while operations requiring strict formal accuracy are assigned to specialized deterministic microservices. The proposed approach makes it possible to improve the reliability and predictability of intelligent publishing systems.

Abstract:

Analysis of various presentations for context free grammars provided with parser generators. A new description format of context free grammars is proposed. Given a representation of context free grammar in JSON format. The concept of a new parser generator based on JSON data format of describing context free grammars is presented. Described a parser generation scheme based on that concept.

Abstract:

This paper addresses the challenge of developing specialized corpus resources for the automated analysis of political manipulation in Russian-language media discourse. Although semantic text analysis and computational discourse analysis have advanced substantially in recent years, most existing corpora and annotation schemes are designed for English-language data and do not adequately capture the linguistic and discursive characteristics of Russian-language news media. The objective of this study is to construct a specialized corpus of Russian-language news texts and to develop an annotation scheme tailored to the automated analysis of political manipulation, with explicit consideration of the linguistic and discursive features of the Russian-language media environment. The study introduces a corpus of sentence-level fragments extracted from Russian-language news texts published between 2010 and 2019, together with an annotation scheme for manipulative techniques. The scheme is based on an adaptation of established international classifications of manipulative strategies and is reduced to a limited set of interpretable techniques relevant to Russian-language news discourse. The proposed framework covers emotional, argumentative, and contextual forms of manipulative influence. The resulting corpus and annotation scheme provide an empirical foundation for the development and evaluation of automated methods for analyzing political manipulation in Russian-language news media and may also support further research in media and political discourse.

Abstract:

A study was conducted on searching for similar documents. The goal was to create a recommendation algorithm for finding similar scientific articles in mathematics using a prioritized search of mathematical formulas with textual support.

The text was converted from graphical to textual representation using OCR technology for subsequent analysis and indexing. During the analysis process, the text was divided into blocks, followed by the extraction of significant formulas, keywords, and phrases from the text. During the indexing process, a vector database was formed based on vector representations of formulas obtained through the embedding process. The indexing results were used to search for articles that are similar to the document submitted by the user to the algorithm input. A list of similar articles is displayed with results sorted by the metric of closeness of vector representations of formulas.

The source data consisted of approximately 5,000 scientific articles devoted to various studies on mathematical topics and presented as PDF files. The experiment was conducted based on data from specific library system content, but the proposed technology can be extended to other library systems, including those containing articles on other topics, such as physics and other exact sciences.

Abstract:

This article discusses the use of stylometric analysis in searching for borrowings of text in the Tatar language. Relevant tools have been developed, utilizing machine learn-ing algorithms, including clustering (k-means method), classification (random forest method, support vector machine method, naive Bayes classifier), and a hybrid approach (FastText model + logistic regression). Special attention is paid to the adaptation of lin-guistic metrics for the Tatar language.

Abstract:

This paper presents a method for the automated attribution of archival handwritten letters based on a Siamese neural network, addressing a key challenge in digital humanities – the authentication of historical documents. The research is motivated by the mass digitization of 17th to 19th-century archives, where attribution is often hindered by incomplete or inaccurate metadata about the authors.

The method is designed for real-world document collections and accounts for challenges typical of archival materials: poor-quality scans, significant handwriting variation, and substantial class imbalance (from 1 to over 50 samples per author). The use of a Siamese network architecture enables the extraction of discriminative vector representations (embeddings). Based on these embeddings, the method not only classifies documents by known authors but also effectively identifies manuscripts that do not match any known author in the archive. This significantly narrows down the pool of candidates for subsequent expert verification.

The study introduces a data preprocessing algorithm and provides a comparative analysis of two approaches to text analysis: at the image fragment level (300×300 px) and at the individual text line level. The developed tool offers archivists and philologists an effective solution for the preliminary sorting and attribution of handwritten documents large collections.

Abstract:

The paper discusses the use of machine learning mechanisms, natural language analysis and intellectual search in the field of jurisprudence. The main expected results are the methodology for applying text-based analytics and semantic natural language processing (NLP) algorithms in knowledge management cases in different types of legal practice. The obtained results can be applied in the field of education and knowledge management in a wider context, since the study lies at the union of jurisprudence, mathematical and computer linguistics.

We describe a prototype of a multi-agent system of intellectual analysis of legal texts that is capable of identifying general dependencies on the existing database of legal documents, providing legal cases with similar topics, recommending the most likely outcomes of judicial review.

Abstract: Currently, there are a huge number of works dedicated to semantic role labeling of English texts [1–3]. However, semantic role labeling of Russian texts was an unexplored area for many years due to the lack of train and test corpora. Semantic role labeling of Russian Texts was widely disseminated after the appearance of the FrameBank corpus [4]. In this approach, we analyzed the influence of the word embedding models on the quality of semantic role labeling of Russian texts. Micro- and macro- F1 scores on word2vec [5], fastText [6], ELMo [7] embedding models were calculated. The set of experiments have shown that fastText models averaged slightly better than word2vec models as applied to Russian FrameBank corpus. The higher micro- and macro- F1 scores were obtained on deep tokenized word representation model ELMo in relation to classical shallow embedding models.

Abstract:

The enrichment of educational texts with semantic content (in particular, adding hyperlinks to the pages of the service that displays detailed information about concepts in the text) helps to increase the efficiency of students' assimilation of the material. The existing methods of semantic markup of educational texts do not take into account the structural features of such documents, which leads to excessive recognition of concepts. This article describes the development of the method of automatic annotation of mathematical concepts in educational mathematical texts by adding functionality to account for the structure of an educational document. The main purpose of the method is to process educational materials of the distance education course "Technology for solving planimetric problems". Following a single template when creating course pages allows you to apply an analysis of the web page markup and keywords used by the course creators. The main task in this process is to determine the type of table cell containing text fragments of educational materials. In accordance with the recommendations of the course creators, definitions should be highlighted in the cells containing the task statement, as well as in those blocks where the input data of the task is indicated. The type of table cells is determined by analyzing their attributes and searching for keywords in their contents. This limitation of recognizable text fragments will improve the student's perception of the course pages and improve the quality of learning.

Abstract:

Handwritten archival documents form a fundamental part of humanity's cultural heritage. However, their analysis remains a labor-intensive task for professional researchers, such as historians, philologists, and linguists. Unlike commercial OCR applications, working with historical manuscripts requires a fundamentally different approach due to the extreme diversity of handwriting, the presence of corrections, and material degradation.

This paper proposes a method for searching within handwritten texts based on stroke segmentation. Instead of performing full text recognition, which is often unattainable for historical documents, this method allows for efficiently answering researcher search queries. The key idea involves decomposing the text into elementary strokes, forming semantic vector representations using contrastive learning, followed by clustering and classification to create an adaptive handwriting dictionary.

It is experimentally shown that search by comparing tuples of reduced sequences of the most informative strokes using the Levenshtein distance provides sufficient quality for the task at hand. The method demonstrates resilience to individual handwriting characteristics and writing variations, which is particularly important for working with authors' archives and historical documents.

The proposed approach opens up new possibilities for accelerating scientific research in the humanities, reducing the time required to find relevant information from weeks to minutes, thereby qualitatively transforming research capabilities when working with large archives of handwritten documents.

Abstract:

This paper addresses the issue of automatic annotation of training datasets in the field of computer vision using machine learning methods. Data annotation is a key stage in the development and training of deep learning models, yet the process of creating labeled data often requires significant time and labor. This paper proposes a mechanism for automatic annotation based on the use of convolutional neural networks (CNN) and active learning methods.

The proposed methodology includes the analysis and evaluation of existing approaches to automatic annotation. The effectiveness of the proposed solutions is assessed on publicly available datasets. The results demonstrate that the proposed method significantly reduces the time required for data annotation, although operator intervention is still necessary.

The literature review includes an analysis of modern annotation methods and existing automatic systems, providing a better understanding of the context and advantages of the proposed approach. The conclusion discusses achievements, limitations, and possible directions for future research in this field.

Abstract:

The aim of the work is to identify key topics in modern psychological research of cultural congruence using the method of thematic digital modeling of an array of scientific publications.

The modernity and significance of the conducted research is due to the growing importance of cultural congruence in the context of the digital transformation of society, which is changing the ways of socialization and interaction. Modern technologies require rethinking the psychological mechanisms of individual adaptation to the cultural environment, especially in childhood and adolescence. Despite the active study of this phenomenon, there is a noticeable shortage of research on the cultural congruence of adults. The use of digital modeling and artificial intelligence allows us to systematize knowledge and identify the structure of the thematic field with high accuracy. The obtained data opens up the prospect for further study of cultural congruence throughout the entire life cycle.

The thematic field review of cultural congruence research was conducted based on an analysis of digital archives comprising a curated collection of 112 scholarly publications on the topic. The review employed a topic modeling algorithm implemented in the Python programming language and leveraged digital platforms incorporating multimodal neural network–based tools (GigaChat, Qwen, DeepSeek). The data analysis yielded four distinct age groups that reflect the developmental specificity of cultural congruence manifestations: preschoolers, primary school–age children, adolescents, and adults.

Abstract:

This article discusses the impact of global interpreter blocking on the performance of multithreaded applications in Python. The concept of subinterpreters is described as one of the solutions that allows bypassing the limitations of the GIL and ensuring effective parallel code execution. A comparative analysis of subinterpretors with traditional methods of parallel computing, such as the use of processes and threads, is carried out. The experimental results show that subinterpreters significantly increase performance under conditions of high computing loads. In addition, the article explores the use of subinterpreters in web development. The advantages of using this approach for query processing and resource management in modern web applications are considered, which can significantly improve their scalability and responsiveness. The novelty of this work lies in the in-depth analysis of subinterpreters in the context of specific use cases, which has previously not received sufficient coverage in the scientific literature. The results of the work emphasize the need for further study of subinterpreters as an alternative approach in Python, which is of interest to developers and researchers in the field of high-performance computing.

Abstract:

Emotion recognition in text represents an important task in natural language processing. This study investigates the influence of verb morphological form on emotion classification performance by encoder models and identifies factors that may determine morphological sensitivity in language models. Three models (ruBERT-tiny2, ruBERT-base, ruRoBERTa-large), fine-tuned on a combined corpus of four Russian-language datasets (22,852 examples), were employed in the experiment. Each model classified 5,676 morphological forms of 473 verbs from the Russian Emotion Lexicon. Results revealed systematic morphological influence: differences in classification performance between forms, as measured by F1-score, reached 20–25% across all models. To account for the observed patterns, training data characteristics were analysed. Frequency of morphological forms in the corpus was shown to partially correlate with classification performance, though it does not appear to be the sole determining factor. Analysis of emotion distribution across morphological forms revealed that in the training corpus, imperative forms occur predominantly in contexts associated with Joy. However, Sadness-labelled verbs in imperative mood are systematically classified by encoders as Anger. This discrepancy between training data characteristics and classification outcomes suggests that imperatives combined with sadness semantics are interpreted by models as expressions of aggression, indicating an interaction between grammatical form and verb semantics in determining emotion class.

Abstract:

A formalized method for the automated detection of software requirement changes during the evolution of technical documentation versions is described. The input data consist of sets of requirements extracted and classified into functional and non-functional categories, with further granularity regarding non-functional requirement types (e.g., performance, security, availability, etc.) for each documentation version. The task of matching requirements between versions is reduced to constructing a partial mapping between the requirement sets and assigning one of the following statuses to each requirement: Unchanged, Modified, New, or Deleted.

A composite similarity function for requirement pairs is proposed, integrating semantic similarity based on vector representations (embeddings), lexical similarity, requirement class consistency, and the structural context of the document. The results of applying the proposed method to an open dataset of requirement pairs are presented. A prototype system for requirement change analysis in technical documentation has been developed.

Abstract: In this paper, we propose a method of machine-generated and non-scientific text detection in a collection of scientific papers. The method is based on lexical and morphological analysis of the document examined with the help of language modeling. This technique enables estimation of probability that the text belongs to the class of scientific documents. Experimental evidence shows feasibility of the approach.

Abstract:

A new precise MCE algorithm for extracting the main content from news websites is presented. The proposed algorithm uses analysis of the Document Object Model (DOM) structure and content density metrics to identify and extract the informational core of a web page. The implemented approach combines three key features: the maximum number of direct child elements containing text, the maximum textual content without child elements containing text, and the closest position to the average node depth. The algorithm demonstrated superior performance compared to existing solutions such as Boilerpipe and Readability, achieving 99.96% precision, 99.69% recall, and 99.80% F1-score on a comprehensive dataset of 500 diverse web pages. Its language-independent design makes the algorithm particularly effective for extracting multilingual content, including languages with complex structures such as Arabic.

Abstract:

The paper proposes software mechanisms aimed at enhancing video production processes for the authors of artistic video materials. We propose a mechanism for creating animated three-dimensional shooting plans (storyboards) using augmented reality to position and animate the movement of actors. In order to overcome the limitations of the iOS operating system related to access to sensors, we developed a mechanism for separately capturing audio and video streams from device sensors for recording and their subsequent synchronization by timestamps for saving to device memory. Computer vision technologies are used to ensure compliance with the rules of compositional construction and image quality analysis. The paper also presents mechanisms for working with the script, including text processing algorithms for displaying subtitles on the screen, and speech recognition algorithms for comparing speech recognition of actors with the text of the script.

Abstract:

This article provides an overview of existing solutions for semantic analysis of mathematical documents, and also presents a method for automatic semantic analysis of documents in PDF format. This method searches for local variables in the text of the article, extracts their definitions and connects concepts with formulas. The advantage of the method over the existing ones is independence from the markup of the original PDF document, which expands the scope of the method. We provide estimates of recall, precision and F-measure for algorithms for finding variables and linking local variables with formulas. The resulting semantic markup of the document will be used to create a collection of documents suitable for the semantic formula search service, which is part of the set of services of the Lobachevskii-DML digital publishing system.

Abstract:

The publishing cycle is currently undergoing significant technological changes: automated publication management systems are being implemented, neural network technologies are being used for content processing, and tools for the intelligent analysis of scientific data are being actively developed. One of the key trends is the automation of the publishing cycle, aimed at accelerating manuscript processing, improving the quality of metadata, and ensuring the interoperability of information resources. In this context, metadata serves as a connecting element for machine processing and navigation within the scientific knowledge space, ensuring the structuring, interpretation, and integration of information into digital library systems. However, metadata for scientific publications often contain errors, inaccuracies, or are incomplete, and their manual creation and refinement are time-consuming and do not ensure high accuracy. The aim of this work is to design and develop a system for the automatic generation, processing, and management of metadata for scientific documents based on data obtained from scientific publication search services and open knowledge bases. The system can be used to automate the process of extracting, refining, and supplementing the metadata of scientific publications for the purpose of subsequently creating electronic collections of scientific documents.