The performance characteristics and certain maintenance aspects of a natural language querying (NLQ) interface depend on how the data model is conceptualized. One of the areas where alternative conceptualizations are available is events and their specialization. The concept of event specialization is already known from event extraction methods, which allows for a more precise description of the events identified in a text. In the context of NLQ interfaces, event specialization allows narrower or broader questions. This study investigates how the choice of event specialization strategy in OWL (Web Ontology Language) ontologies affects the complexity and performance-related aspects of the NLQ interface to ontologies. In this paper, we present four event specialization strategies and investigate how they impact the size of the ontology schema and vocabulary of the NLQ interface, the performance of querying and data import, the size of the semantic repository, and the complexity of SPARQL queries. We discuss the strengths and weaknesses of each approach and present recommendations on determining the best one for the needs of NLQ interface end-users and developers.

Online hate speech and abusive language pose a growing challenge for content moderation, especially in multilingual settings and for low-resource languages such as Lithuanian. This paper investigates to what extent modern multilingual sentence embedding models can support accurate hate speech detection in Lithuanian, Russian, and English, and how their performance depends on downstream modeling choices and feature dimensionality. We introduce LtHate, a new Lithuanian hate speech corpus derived from news portals and social networks, and benchmark six modern multilingual encoders (gemma, qwen, bge, snow, jina, and e5) on LtHate, RuToxic, and EnSuperset using a unified Python pipeline. For each embedding type, we train both a one-class histogram-based anomaly detector (HBOS) and a two-class gradient-boosted tree ensemble (CatBoost), with and without Principal Component Analysis (PCA) compression to 32-dimensional feature vectors. Across all datasets, two-class supervised models consistently and substantially outperform one-class anomaly detection, with the best configurations achieving up to 78.8% accuracy (Kappa 0.58, AUC ROC 0.87) in Lithuanian (jina), 92.2% accuracy (Kappa 0.77, AUC ROC 0.97) in Russian (e5), and 76.9% accuracy (Kappa 0.48, AUC ROC 0.86) in English (e5). PCA compression deteriorates the discriminative power of CatBoost only slightly, with much more negative impact for the HBOS model. These results demonstrate how modern multilingual sentence embeddings combined with gradient-boosted decision trees provides robust machine learning solutions for multilingual hate speech detection applications.

This paper examines whether incremental prompt engineering can enable reliable LLM based pre-annotation of corpus texts in a low resource language setting. Using Lithuanian as a case study, we systematically evaluate multiple LLM prompt designs and assess their suitability for generating emotional manipulation annotations for corpus development. We find that performance varies with task complexity, and systematic prompt refinement measurably reduces output instability. Cross-model evaluation of the best-performing prompting strategy shows consistent and similar trends over several modern LLMs. Our results demonstrate that while structured prompts substantially improve output consistency and LLM assisted annotation can roughly approximate human produced labels for well-defined categories, the quality of results produced by contemporary LLMs is unsatisfactory for automatic pre-annotation of emotional manipulation techniques in a low resource language.

This paper examines whether incremental prompt engineering can enable reliable large language model (LLM)-based pre-annotation of corpus texts in a low-resource language setting. Using Lithuanian as a case study, we systematically evaluate multiple LLM prompt designs and assess their suitability for generating emotional manipulation annotations for corpus development. We find that performance varies with task complexity, and systematic prompt refinement measurably reduces output instability. Cross-model evaluation of the best-performing prompting strategy shows consistent and similar trends over several modern LLMs. Our results demonstrate that while structured prompts substantially improve output consistency and LLM-assisted annotation can roughly approximate human-produced labels for well-defined categories, the quality of results produced by contemporary LLMs is unsatisfactory for automatic pre-annotation of emotional manipulation techniques in a low-resource language.