1. |
2. Dataset of Uzbek base words : extraction and data analysis based on the school corpusKhabibulla Madatov, Surayyo Khajibaeva, Jernej Vičič, 2026, izvirni znanstveni članek Opis: The article presents a dataset of Uzbek base words extracted from a purposefully prepared corpus using the Synonym Thesaurus Support method. This method identifies base words for each school-grade by analysing a large text corpus comprising 142 textbooks intended for school education in Uzbekistan. The definition of the base word used in this article and in the proposed dataset is a word within a synonymic series that: - is the most widely used. - is distinguished by semantic clarity and stability. - has stylistic neutrality. Based on the proposed approach, school textbooks were analysed by dividing them into Primary (school grades 1 - 4), Basic Secondary (school grades 5 - 9), and Secondary (school grades 10 - 11) blocks. Base words that stand out from the general corpus were identified for each school-grade. This method extracted new base words not found in previous school grades and specific to the observed grade. The main idea of the method is to extract base words from the lemma sset of each school-grade using a corpus of synonyms. This allows analysing the level of lexical complexity and class-specific vocabulary richness of texts intended for schoolchildren. The final results are lists of base words specifically extracted from primary (school-grades 1 - 4), basic secondary (school-grades 5 - 9), and secondary (school-grades 10 - 11) school texts; 17,599,48,203, and 20,491 base words, respectively.
Ključne besede: school corpus, base word, basic vocabulary, Uzbek language
Objavljeno v RUP: 20.05.2026; Ogledov: 455; Prenosov: 14
 Celotno besedilo (2,42 MB)
Gradivo ima več datotek! Več... |
3. Analiza sentimenta bosanskega jezika : doktorska disertacijaSead Jahić, 2026, doktorska disertacija Ključne besede: Bosnian, sentiment analysis, negation, intensifiers, machine learning, classifier, neural networks, BoSA, BOSentiment
Objavljeno v RUP: 12.03.2026; Ogledov: 784; Prenosov: 50
Celotno besedilo (3,04 MB)
Gradivo ima več datotek! Več... |
4. Dataset of sentiment tagged language resources for Macedonian languageSofija Kochovska, Jernej Vičič, Branko Kavšek, 2026, izvirni znanstveni članek Opis: Macedonian is a South Slavic language spoken by about 2 million people, primarily in North Macedonia and among diaspora communities worldwide. It’s known for a few distinctive features. Most notably, it uses definite articles attached to the end of nouns, for example, kniga (a book) becomes knigata (the book). Furthermore, it doesn’t use grammatical cases, which makes its grammar relatively straightforward compared to other Slavic languages. The dataset comprises two lists of sentiment annotated words that present the core of the Macedonian sentiment-annotated lexicon, a list of the stopwords, and a list of Affirmative and non-Affirmative words (AnAwords) composed mostly of intensifiers and diminishers, and a list of polarity shifters. The main usage of the presented materials is in rule-based sentiment analysis, but the usage of some of the lists can be much broader.
Ključne besede: Macedonian language, sentiment analysis, sentiment lexicon, sentiment analys, rule-based methods, natural language processing, low-resource languages, AnA words, stopwords, intensifiers, diminishers, polarity shifters
Objavljeno v RUP: 20.01.2026; Ogledov: 792; Prenosov: 5
Celotno besedilo (251,79 KB)
Gradivo ima več datotek! Več... |
5. TF-IDF-based classification of Uzbek educational textsKhabibulla Madatov, Sapura Sattarova, Jernej Vičič, 2025, izvirni znanstveni članek Opis: This paper presents a baseline study on automatic Uzbek text classification. Uzbek is a morphologically rich and low-resource language, which makes reliable preprocessing and evaluation challenging. The approach integrates Term Frequency–Inverse Document Frequency (TF–IDF) representation with three conventional methods: linear regression (LR), k-Nearest Neighbors (k-NN), and cosine similarity (CS, implemented as a 1-NN retrieval model). The objective is to categorize school learning materials by grade level (grades 5–11) to support improved alignment between curricular texts and students’ intellectual development. A balanced dataset of Uzbek school textbooks across different subjects was constructed, preprocessed with standard NLP tools, and converted into TF–IDF vectors. Experimental results on the internal test set of 70 files show that LR achieved 92.9% accuracy (precision = 0.94, recall = 0.93, F1 = 0.93), while CS performed comparably with 91.4% accuracy (precision = 0.92, recall = 0.91, F1 = 0.92). In contrast, k-NN obtained only 28.6% accuracy, confirming its weakness in high-dimensional sparse feature spaces. External evaluation on seven Uzbek literary works further demonstrated that LR and CS yielded consistent and interpretable grade-level mappings, whereas k-NN results were unstable. Overall, the findings establish reliable baselines for Uzbek educational text classification and highlight the potential of extending beyond lexical overlap toward semantically richer models in future work.
Ključne besede: Uzbek language, text classification, low-resource languages, TF-IDF, cosine similarity, linear regression, k-Nearest Neighbors
Objavljeno v RUP: 17.10.2025; Ogledov: 1080; Prenosov: 11
Celotno besedilo (286,87 KB)
Gradivo ima več datotek! Več... |
6. Is open source the future of AI? : a data-driven approachDomen Vake, Bogdan Šinik, Jernej Vičič, Aleksandar Tošić, 2025, izvirni znanstveni članek Opis: Large language models (LLMs) have become central to both academic research and industrial applications, fueling debates on their accuracy, usability, privacy, and potential misuse. While proprietary models benefit from substantial investments in data and computing resources, open-sourcing is often suggested as a means to enhance trust and transparency. Yet, open-sourcing comes with its own challenges, such as risks of illicit applications, limited financial incentives, and intellectual property concerns. Positioned between these extremes are hybrid approaches—including partially open models and licensing restrictions—that aim to balance openness with control. In this paper, we adopt a data-driven approach to examine the open-source development of LLMs. By analyzing contributions in model improvements, modifications, and methodologies, we assess how community efforts impact model performance. Our findings indicate that the open-source community can significantly enhance models, demonstrating that community-driven modifications can yield efficiency gains without compromising performance. Moreover, our analysis reveals distinct trends in community growth and highlights which architectures benefit disproportionately from open-source engagement. These insights provide an empirical foundation to inform balanced discussions among industry experts and policymakers on the future direction of AI development.
Ključne besede: large language models, artificial intelligence, open source, data science, HuggingFace
Objavljeno v RUP: 25.09.2025; Ogledov: 1662; Prenosov: 8
Celotno besedilo (606,12 KB)
Gradivo ima več datotek! Več... |
7. |
8. Dataset of vocabulary in Uzbek primary education : extraction and analysis in case of the school corpusKhabibulla Madatov, Sapura Sattarova, Jernej Vičič, 2025, izvirni znanstveni članek Opis: The main goal of this research work is to determine the number of new words that a primary school pupil should know/acquire during each academic year. To accomplish this, we have created two datasets. The first dataset was compiled based on the "Explanatory Vocabulary of the Uzbek Language" (EDUL). The second dataset was created from 35 primary school textbooks for grades 1-4 approved by the Ministry of Preschool and School Education of the Republic of Uzbekistan, and it was named the "Uzbek Primary School Corpus" (UPSC) by authors. Using the "Comparative Lemma Extraction Method" (CLEM) proposed by the authors of the article, a vocabulary for grades 1-4 was created, and the problem of determining the number of new words (disregarding word forms as Uzbek is a morphologically rich language) that primary school pupils should learn each academic year was solved.
Ključne besede: Uzbek language, primary school, corpus construction, natural language processing (NLP), comparative Lemma extraction method
Objavljeno v RUP: 08.08.2025; Ogledov: 1282; Prenosov: 11
Celotno besedilo (342,87 KB)
Gradivo ima več datotek! Več... |
9. Bridging the question–answer gap in retrieval-augmented generation : hypothetical prompt embeddingsDomen Vake, Jernej Vičič, Aleksandar Tošić, 2025, izvirni znanstveni članek Opis: Retrieval-Augmented Generation (RAG) systems synergize retrieval mechanisms with generative language models to enhance the accuracy and relevance of responses. However, bridging the style gap between user queries and relevant information in document text remains a persistent challenge in retrieval-augmented systems, often addressed by runtime solutions (e.g., Hypothetical Document Embeddings (HyDE)) that attempt to improve alignment but introduce extra computational overhead at query time. To address these challenges, we propose Hypothetical Prompt Embeddings (HyPE), a framework that shifts the generation of hypothetical content from query time to the indexing phase. By precomputing multiple hypothetical prompts for each data chunk and embedding the chunk in place of the prompt, HyPE transforms retrieval into a question-question matching task, bypassing the need for runtime synthetic answer generation. This approach does not introduce latency but also strengthens the alignment between queries and relevant context. Our experimental results on six common datasets show that HyPE can improve retrieval context precision by up to 42 percentage points and claim recall by up to 45 percentage points, compared to standard approaches, while remaining compatible with re-ranking, multi-vector retrieval, query decomposition, and other RAG advancements.
Ključne besede: LLM, hypothetical prompt embedding, Retrieval-Augmented Generation (RAG)
Objavljeno v RUP: 04.08.2025; Ogledov: 1818; Prenosov: 42
Celotno besedilo (1,41 MB)
Gradivo ima več datotek! Več... |
10. |
