This paper presents a dataset of Lithuanian language comments annotated with emotional manipulation techniques. The source material comprises comments from Lithuanian news portal texts. A total of 1000 comments were selected and manually annotated by four human annotators using Label Studio. The annotators identified text fragments corresponding to fourteen emotional manipulation techniques, producing span-level human annotations that form the primary component of the dataset.In addition to the manual annotations, the dataset includes machine-generated outputs created by the GPT-4.1 model. These outputs were produced by executing prompts designed for the detection and classification of emotional manipulation span. Several prompting strategies were applied, and each prompt was run five times to capture variability in model behaviour. Because GPT-4.1 does not always return verbatim text excerpts, all generated spans were post-processed to extract precise fragments from the original comments and compute their character-level offsets.The resulting dataset encompasses four components: unprocessed source comments, human-annotated spans, prompt templates, and GPT-4.1 generated predictions.The dataset provides the first publicly available Lithuanian resource annotated for emotional manipulation techniques and can support research on manipulation and persuasion phenomena in a morphologically rich, low-resource language. The human annotations may be used as a benchmark for evaluating computational models for span extraction and technique classification. The inclusion of prompts and corresponding GPT-4.1 outputs enables the study of large language model behaviour under different prompting strategies and facilitates prompt engineering research without repeating inference runs. The dataset may also be reused for training or evaluating multilingual and cross-lingual models and offers a foundational framework for the development of annotation schemes and guidelines in related corpus construction efforts.

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.

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.

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.

Open online courses are often used in formal education to provide added value for the students by helping gain new skills and competences or as extra material tasks in addition to the formal education course. The course described in this paper is developed and piloted fully open online. It is also integrated into formal education. This paper presents a case on integration of open databases course into formal education together with student feedback on the course quality and effectiveness of course delivery process.

Information in knowledge graphs is ordinarily accessed via queries in formal languages. Formal languages, however, present an obstacle for non-technical users. To make semantic search more convenient, it is desirable to enable use of natural language queries. One of the difficulties encountered in developing natural language querying systems is a mismatch between the way how users express their questions in a natural language and the way how a knowledge graph is structured. Such a mismatch is called semantic gap. One of the solutions for bridging the semantic gap is to use SBVR vocabularies for translation between the natural and formal languages. In this article, we investigate how alternative variants of event representation schemas affect properties of natural language querying interface: the size of ontology schema and vocabulary, the performance of querying and data import, repository size and query complexity.

The daily growth of unstructured textual information created on the Web raises significant challenges when it comes to serving user information needs. On the other hand, evolving Semantic Web technology has influenced a wide body of research towards meaning-based text processing and information retrieval methods, that go beyond classical keyword-driven approaches. However, most of the work in the field targets English as the primary language of interest. Hence, in this paper we present a very first attempt to process unstructured Lithuanian text at the level of ontological semantics. We introduce an ontology-based semantic search framework capable of answering structured natural Lithuanian language questions, discuss its language-dependent design decisions and draw some observations from the results of a recent case study carried out over domain-specific Lithuanian web news corpus.

The semantic search over ontologies allows user to retrieve more relevant results comparing with ordinary keyword based search systems. This type of search system is powered by ontologies and the most convenient interface to ontologies is natural language interface. In this paper, we present multilingual SBVR standard based natural language interface to ontologies, which allows writing questions based on concepts of SBVR vocabulary and transforms them to SPARQL queries using model transformations. The solution can also be used for questioning, when question mapping to ontology is not straightforward. The experimental evaluation of correctness using Mooney Natural Language Learning Data showed results, similar to other natural language interface solutions, answering questions in English and Lithuanian languages.

SBVR is the richest knowledge model allowing to create specifications that are understandable for business people and also interpretable by computers. Existing SBVR editors still lack capabilities that could allow generating formal SBVR models, adapting SBVR to several languages or making SBVR extensions for various purposes without changing SBVR metamodel.The goal of the paper is to present the Xtext grammar for SBVR structured language and the prototype of SBVR editor, created on the base of this grammar. The experiment conducted with the prototype has shown that it allows defining business vocabularies, business rules and questions in SBVR structured English and Lithuanian languages; produxing formal SBVR models; using concepts from several vocabularies , and extending SBVR without changing its metamodel. DOI: http://dx.doi.org/10.5755/j01.itc.45.1.9219

The continuous growth of unstructured textual information on the web implies the need for novel, semantically aware content processing and information retrieval (IR) methods. Following the evolution and wide adoption of Semantic Web technology, a number of approaches to overcome the limitations of traditional keyword-based search techniques have been proposed. However, most of the research concentrates on English and other well-known, linguistic resource-rich languages. Hence, this paper presents an attempt to semantic search over domain-specific Lithuanian web documents. We introduce an ontology-based semantic search framework capable of answering structured natural Lithuanian language questions and discuss its language-dependent design decisions. The findings from a recent case study showed that our proposed framework can be applied to approach meaning-based IR with significant results, even when the underlying language is morphologically rich and has limited linguistic resources.

The goal of the paper is to present question patterns in structured natural language and their transformations into ontology query language SPARQL for allowing business participants to communicate with business software services and data in more flexible and friendly way. The structured language is based on Semantics of Business Vocabulary and Business Rules (SBVR) metamodel, which allows creating and managing business vocabularies and business rules in specific domains. The current paper is focused on transforming question patterns, including usage of synonyms and synonymous forms; projecting formulations constrained by atomic formulations based on facts and fact types; projections on several variables; restricting query results by auxiliary variables constrained by various logical formulations; supplementing questions with derivation rules from SBVR vocabulary of business rules, etc. Patterns are followed by examples, proved by implemented SBVR query editor and SBVR to SPARQL transformations.

—The paper presents transformation framework from questions in structured language based on Semantics of Business Vocabulary and Rules (SBVR) into SPARQL queries over ontologies defined in Web Ontology Language OWL 2 and, possibly, supplemented with Semantic Web rules SWRL. Such transformation depends on OWL 2 ontology related with corresponding SBVR vocabulary and rules. The current work considers a family of transformations and metamodels required for relating ontologies, rules, SPARQL queries and real business data supported by computerised information systems, as well as establishes requirements for harmonizing the coexistence and preserving semantics of these different representations.

Today information systems more and more often rely on ontologies that are able to represent meaningful concepts and complex relationships among them relevant for business models and their supporting software systems. However, ontology development and access to ontological data is only possible on deep technological level that is not friendly for business experts. The goal of the paper is to present a possibility of querying OWL ontologies using semantic formulations of Semantics of Business Vocabulary and Business Rules (SBVR), expressed in SBVR Controlled English. We introduce the initial approach for specifying ontology queries as SBVR questions and transforming them to SPARQL.

The OMG SBVR standard is the most mature abstract representation for Business semantics; however, the complexity of SBVR metamodel prevents its broad and rapid usage in business communities. There are a few SBVR implementations yet, but the popularity of SBVR is growing as different interest-groups are finding the variety of ways for applying the SBVR standard. The goal of this paper is to present the VeTIS tool capable for editing SBVR Business Vocabularies and Business Rules and transforming them into UML class models supplemented with OCL constraints. It is integrated into MagicDraw UML CASE tool and organically combines with simple development process, which pursues defining requirements via use cases and modelling business processes via activities.

Relating Semantic Web ontologies with relational databases becomes a topical problem as ontologies provide more and richer capabilities for accessing information that is currently closed in heterogeneous and distributed sources e.g. relational databases. The growing number of tools and methodologies are considering this problem but usually they are looking from the point of view of ontologies or from the point of databases. We propose a hybrid approach where ontology classes and properties are mapped to database schema and instances are stored in database tables while more complex constructs that cannot be adequately represented by database concepts are stored in metadata tables. This allows the lossless, bidirectional transformations between ontologies and databases combining advantages and addressing the needs of both worlds.

The goal of the paper is to present the enhanced database schema for storing ontologies considering new features of OWL 2 and possibilities of querying these ontologies using SPARQL. The growing size of ontologies and the scope of their applications require the effective means for storing ontology data that relational databases already have approved. Many existing ontology reasoning tools are using relational databases for this purpose. However, in practice almost all of them are using the straightforward approach restricted to representing instances whereas the effectiveness of processing ontological data may be considerably improved by keeping information about ontology classes, object properties and more advanced concepts in database tables. Previously we have presented the method and tool for transforming OWL ontologies to relational database. Currently, we have extended our representation with novel concepts of OWL 2, the recent Recommendation of W3C. Also, we present a prototype of a tool for extracting ontologies from relational databases and thus allowing the step-wise processing of SPARQL queries where SPARQL is used for querying ontology structures in a main memory and SQL is used for querying instances in the database.