The rapid growth of scientific literature necessitates effective information extraction. However, existing methods face significant challenges, particularly when applied to multi-domain documents and low-resource languages. For Kazakh and Russian, there is a notable lack of annotated corpora and dedicated tools for scientific information extraction. To address this gap, we introduce SciMDIX (Scientific Multi-Domain Information extraction), a novel multi-domain dataset of scientific documents in Russian and Kazakh, annotated with entities and relations. Our study includes a comprehensive evaluation of entity recognition performance, comparing state-of-the-art models, such as BERT, LLaMA, GLiNER, and spaCy across four diverse domains (IT, Linguistics, Medicine, and Psychology) in both languages. The findings highlight the promise of spaCy and GLiNER for practical deployment in under-resourced language settings. Furthermore, we propose a new zero-shot relation extraction model that leverages a multimodal representation by integrating sentence context, entity mentions, and textual definitions of relation classes. Our model can predict semantic relations between entities in new documents, even for a language encountered during training. This capability is especially valuable for low-resource language scenarios.

The presented paper is devoted to the development of a method for identifying and correcting spelling errors in Kazakh texts. In this paper, the study object is methods for more accurate correction of spelling errors in Kazakh texts. The aim of the study is to develop an augmented version of the Damerau-Levenshtein method for correcting spelling errors in Kazakh language texts. Automatic detection and correction of spelling errors have become a default feature in modern text editors for working with text data, in text messaging applications such as chatbots, messengers, etc. However, although this task is well solved in geographically widespread languages, it has not been fully solved in languages with a small audience, such as the Kazakh language. The methods developed so far cannot correct all spelling errors found in Kazakh texts. Therefore, the development of a method with specific algorithms for spelling error correction in Kazakh texts is considered. As a result of the research work, algorithms for correcting errors found in Kazakh language texts were developed, and the developed algorithms were included in the Damerau-Levenshtein method. The experimental testing results of the augmented Damerau- Levenshtein method showed 97.2 % accuracy in correcting specific errors found only in Kazakh words and 92.8 % accuracy in correcting common errors from letter symbols. The standard Damerau-Levenshtein method testing results showed 76.4 % accuracy in correcting specific errors found only in Kazakh words. The results of the tests in correcting common errors from letter symbols with the standard Damerau-Levenshtein were approximately the same with the augmented Damerau-Levenshtein method, the accuracy is 92.2 %. The extent and conditions of practical application of the results are implemented by including them in text editors, messengers, e-mails and similar applications that work with text data.

The article is devoted to the introduction of digital watermarks, which formthe basis for copyright protection systems. Methods in this area are aimed at embedding hidden markers that are resistant to various container transformations. This paper proposes a method for embedding a digital watermark into bitmap images using Lagrange interpolation and the Bezier curve formula for five points, called Lagrange interpolation along the Bezier curve 5 (LIBC5). As a means of steganalysis, the RS method was used, which uses a sensitive method of double statistics obtained on the basis of spatial correlations in images. The output value of the RS analysis is the estimated length of the message in the image under study. The stability of the developed LIBC5 method to the detection of message transmission by the RS method has been experimentally determined. The developed method proved to be resistant to RS analysis. A study of the LIBC5 method showed an improvement in quilting resistance compared to that of the INMI image embedding method, which also uses Lagrange interpolation. Thus, the LIBC5 stegosystem can be successfully used to protect confidential data and copyrights.

In this paper calculation and formation of aggregational values being the main elements of operative analysis of multidimensional data, in the form of hypercube and the development of effective correlation structure to the data during the process of the analytical analysis are considered. In the course of writing, basic concepts of multidimensional data model and internal structure are given. Measurements used for the implementation of hypercube and for the description of dimension elements the sequence of sets theory is applied. Pre-calculation of all aggregation values for quick operative analysis and in order to carry out the effective correlation to the values received in the result of calculation, multidimensional indexing are developed. In this structure, in accordance with the primary keys intersection of dimensional elements multidimensional indexing structure having been formed and pre-aggregation is made for the initial quantitative values through the formed multidimensional indexing structure. Pre-aggregation values in separate structure is stored and according to multidimensional indexing the pointer is installed to the aggregational value address. This means one multidimensional index matched with one value. After the termination of pre-aggregational values calculation, calculations of aggregational values that are solved in all the intersections of the values are considered. In the end of paper conclusion and literature are given.

This study presents the development of an Artificial Intelligence (AI)-based legal assistant using the Retrieval-Augmented Generation (RAG) architecture to provide legal assistance to citizens of the Republic of Kazakhstan. The proposed solution is designed to generate accurate, evidence-based responses to user queries using the regulatory legal acts of the Republic of Kazakhstan as the primary source of information. A legal corpus comprising 101,000 legislative documents and court decisions, with approximately 77 million tokens in Kazakh and Russian, was constructed to support the retrieval component of the system. To identify the most effective semantic retrieval method, three multilingual embedding models—Multilingual-E5-Large, BGE-M3, and KazEmbed-V5—were evaluated for vector search. The experimental results showed retrieval accuracies of 87.6%, 76.8%, and 83.3%, respectively. The GPT-5.4 and Llama-4-Scout-17B-16E-Instruct large language models were used to generate legal reasoning and responses based on documents retrieved through semantic search. The quality of the generated responses was evaluated using two complementary approaches. First, legal experts assessed the factual correctness and legal validity of the answers. Second, automatic evaluation was performed using word-level F1, BLEU, ROUGE, and BERTScore-F1 metrics. Among all evaluated configurations, GPT-5.4 combined with Multilingual-E5-Large achieved the highest overall accuracy (88.5%), whereas Llama-4-Scout-17B-16E-Instruct combined with KazEmbed-V5 achieved an accuracy of 83.6%. Based on the proposed architecture and the selected semantic retrieval and language models, an AI legal assistant was developed and integrated into the “Adal Azamat” legal services platform providing users in Kazakhstan with practical access to AI-assisted legal consultation.

This study delves into the relatively unexplored domain of natural language processing for the Kazakh language—a language with limited computational resources. The paper dissects the effectiveness of diffusion models and transformers in generating text, specifically paraphrases, which is a critical aspect of machine learning applications such as chatbots, virtual assistants, and automated translation services. The researchers methodically adapt these advanced models to understand and generate Kazakh text, tackling the unique challenges posed by the language's complex morphology. The paper is comprehensive in its approach, covering everything from the initial adaptation of the models to the Kazakh language context, to the creation of specialized tokenizer tools, to the translation and preparation of datasets for effective training. Through rigorous testing and performance analysis, the study identifies the strengths and weaknesses of each model type. This is critical as it informs the direction of future research and model development, with the goal of enhancing the fluency and accuracy of automated Kazakh text generation. The paper also discusses the broader impact of its findings, suggesting that the methodologies and insights gained could inform similar efforts in other low-resource languages, thereby contributing to the global field of NLP. The research concludes with reflections on the implications of their findings for the ongoing development of machine learning technologies, asserting the potential of these technologies to accommodate the intricacies of any language, given the right approach and resources. This work not only advances the technical capabilities for Kazakh text generation but also serves as a testament to the potential of machine learning to bridge language gaps and foster greater digital inclusivity. Данное исследование углубляется в относительно неисследованную область обработки естественного языка казахского языка — языка с ограниченными вычислительными ресурсами. В статье анализируется эффективность моделей диффузии и преобразователей при создании текста, в частности перефразирования, что является важнейшим аспектом приложений машинного обучения, таких как чат-боты, виртуальные помощники и службы автоматического перевода. Исследователи методично адаптируют эти передовые модели для понимания и создания казахского текста, решая уникальные проблемы, возникающие из-за сложной морфологии языка. Статья носит комплексный подход и охватывает все: от первоначальной адаптации моделей к контексту казахского языка до создания специализированных инструментов токенизатора, перевода и подготовки наборов данных для эффективного обучения. Благодаря тщательному тестированию и анализу производительности исследование выявляет сильные и слабые стороны каждого типа модели. Это имеет решающее значение, поскольку определяет направление будущих исследований и разработки моделей с целью повышения беглости и точности автоматического создания казахского текста. В документе также обсуждается более широкое влияние своих выводов, предполагая, что полученные методологии и идеи могут послужить основой для аналогичных усилий на других языках с ограниченными ресурсами, тем самым способствуя глобальному развитию НЛП. Исследование завершается размышлениями о последствиях их выводов для продолжающегося развития технологий машинного обучения, утверждая потенциал этих технологий для решения сложностей любого языка при правильном подходе и ресурсах. Эта работа не только расширяет технические возможности создания казахского текста, но и служит свидетельством потенциала машинного обучения для преодоления языковых разрывов и содействия большей цифровой инклюзивности. Бұл зерттеу қазақ тілі үшін табиғи тілді өңдеудің салыстырмалы түрде зерттелмеген саласын - есептеу ресурстары шектеулі тілді зерттейді. Бұл мақалада чат-боттар, виртуалды көмекшілер және автоматтандырылған аударма қызметтері сияқты машиналық оқыту қолданбаларының маңызды аспектісі болып табылатын мәтінді, атап айтқанда парафразаларды құрудағы...