Persuasion techniques are powerful rhetorical devices used to sway public opinion in a wide range of media. We present a new corpus of persuasion techniques, focusing on Slavic languages. The corpus contains documents in Bulgarian, Polish, and Russian, annotated with persuasion techniques at the coarse-grained text-span level and fine-grained sentence level. The techniques are drawn from a taxonomy of 25 fine-grained persuasion techniques, grouped under six broad categories of rhetorical persuasion strategies. The corpus contains approximately 7500 text spans from 222 documents that cover topics hotly debated at the national and international levels. We describe the corpus creation process, provide detailed statistics, and examine correlations between topics and persuasion techniques. We use classic ML-based and generative AI-based models to provide baselines and benchmark results for the detection and classification of persuasion techniques at the text-span level and sentence level.

Reliable Text Difficulty Assessment is a prerequisite for valid text simplification workflows and personalized learning applications. However, the development of robust assessment models is severely hindered by a critical bottleneck: the scarcity of expert-annotated corpora containing fine-grained difficulty levels (e.g., CEFR), particularly for lower-resource languages. This paper addresses this data scarcity problem in the context of a low-resource European language. We propose a cross-lingual data augmentation strategy that leverages machine translation to transfer labeled resources from high-resource languages to the target low-resource language. We train BERT-based regression models to predict difficulty scores and investigate whether synthetic, translated data can effectively supplement native training sets. Our experiments demonstrate that augmenting scarce native data with machine-translated corpora significantly improves the accuracy of difficulty estimation, offering a viable solution for languages lacking extensive expert annotations.

We present SlavicNLP 2025 Shared Task on Detection and Classification of Persuasion Techniques in Parliamentary Debates and Social Media. The task is structured into two subtasks: (1) Detection, to determine whether a given text fragment contains persuasion techniques, and (2) Classification, to determine for a given text fragment which persuasion techniques are present therein using a taxonomy of 25 persuasion technique taxonomy. The task focuses on two text genres, namely, parliamentary debates revolving around widely discussed topics, and social media, in five languages: Bulgarian, Croatian, Polish, Russian and Slovene. This task contributes to the broader effort of detecting and understanding manipulative attempts in various contexts. There were 15 teams that registered to participate in the task, of which 9 teams submitted a total of circa 220 system responses and described their approaches in 9 system description papers.

Easy language and text simplification are currently topical research questions, with important applications in many contexts, and with various approaches under active investigation, including prompt-based methods. The estimation of the level of difficulty of a text becomes crucial when the estimator is employed inside a simplification workflow as a quality-control mechanism. It can act as a critic in frameworks where it can guide other models, which are responsible for generating text at a specified level of difficulty, as determined by the user's needs. We present our work in the context of simplified Finnish. We discuss problems in collecting corpora for training models for estimation of text difficulty, and our experiments with estimation models. The results of the experiments are promising: the models appear usable both for assessment and for deployment as a component in a larger simplification framework.

While Generative AI (GenAI) has the potential to transform knowledge work, its proper application in business remains a challenge. To obtain benefits from GenAI, companies must navigate a complex landscape of technologies and best practices for their implementation. The selection, integration, and implementation of specific GenAI solutions are complex, particularly for small and medium-sized enterprises. To address this issue, we have launched a research and development project named GAIK (Generative AI-enhanced Knowledge Management) to develop a business-oriented GenAI toolkit to improve three processes: knowledge capture, synthesis, and access. The toolkit will include software components (modules and code libraries), guidelines, process models, templates, and reusable knowledge models, enabling companies and technology providers to develop easy-to-deploy knowledge management solutions using business data. This paper describes the envisioned toolkit, its potential use cases, and the required research activities to develop and apply it.

Understanding how linguistic topics are related to each another is essential for designing effective and adaptive second-language (L2) instruction. We present a data-driven framework to model topic dependencies and their difficulty within a L2 learning curriculum. First, we estimate topic difficulty and student ability using a three-parameter Item Response Theory (IRT) model. Second, we construct topic-level knowledge graphs-as directed acyclic graphs (DAGs)-to capture the prerequisite relations among the topics, comparing a threshold-based method with the statistical Grow-Shrink Markov Blanket algorithm. Third, we evaluate the alignment between IRT-inferred topic difficulty and the structure of the graphs using edge-level and global ordering metrics. Finally, we compare the IRT-based estimates of learner ability with assessments of the learners provided by teachers to validate the model's effectiveness in capturing learner proficiency. Our results show a promising agreement between the inferred graphs, IRT estimates, and human teachers' assessments, highlighting the framework's potential to support personalized learning and adaptive curriculum design in intelligent tutoring systems.

We present FRaN-X, a Framing and Narratives Explorer that automatically detects entity mentions and classifies their narrative roles directly from raw text. FRaN-X comprises a two-stage system that combines sequence labeling with fine-grained role classification to reveal how entities are portrayed as protagonists, antagonists, or innocents, using a unique taxonomy of 22 fine-grained roles nested under these three main categories. The system supports five languages (Bulgarian, English, Hindi, Russian, and Portuguese) and two domains (the Russia-Ukraine Conflict and Climate Change). It provides an interactive web interface for media analysts to explore and compare framing across different sources, tackling the challenge of automatically detecting and labeling how entities are framed. Our system allows end users to focus on a single article as well as analyze up to four articles simultaneously. We provide aggregate level analysis including an intuitive graph visualization that highlights the narrative a group of articles are pushing. Our system includes a search feature for users to look up entities of interest, along with a timeline view that allows analysts to track an entity's role transitions across different contexts within the article. The FRaN-X system and the trained models are licensed under an MIT License. FRaN-X is publicly accessible at https://fran-x.streamlit.app/ and a video demonstration is available at https://youtu.be/VZVi-1B6yYk.

This paper presents the integration of AI features into the language-teaching platform, Revita. The system is an intelligent online tutor, developed to support learners from lower-intermediate toward advanced levels, in several languages. Target skills currently include grammar, vocabulary, aural comprehension, and pronunciation. Based on authentic texts uploaded by the learners themselves, the system creates a rich variety of exercises that are tailored to the individual learner’s level of proficiency. Revita’s main guiding principle is personalization, motivated by current theories from educational science, notably Vygotsky’s concept of the Zone of Proximal Development and dynamic assessment, as well as the principles of diagnostic assessment. The linguistic foundation for the system comes from Construction Grammar, the goal being to build a complete inventory of constructions in the target language, as the basis for judging the correctness of the learners’ responses to the exercises. Revita is enhanced with AI tools from natural language processing, machine learning, and educational data mining.

We present NarratEX, a dataset designed for the task of explaining the choice of the Dominant Narrative in a news article, and intended to support the research community in addressing challenges such as discourse polarization and propaganda detection. Our dataset comprises 1,056 news articles in four languages, Bulgarian, English, Portuguese, and Russian, covering two globally significant topics: the Ukraine-Russia War (URW) and Climate Change (CC). Each article is manually annotated with a dominant narrative and sub-narrative labels, and an explanation justifying the chosen labels. We describe the dataset, the process of its creation, and its characteristics. We present experiments with two new proposed tasks: Explaining Dominant Narrative based on Text, which involves writing a concise paragraph to justify the choice of the dominant narrative and sub-narrative of a given text, and Inferring Dominant Narrative from Explanation, which involves predicting the appropriate dominant narrative category based on an explanatory text. The proposed dataset is a valuable resource for advancing research on detecting and mitigating manipulative content, while promoting a deeper understanding of how narratives influence public discourse.

Teaching heritage language presents many challenges, one of the greatest of which arises when the teacher must work with a heterogeneous audience. Our article describes the experiences in integration of an intelligent tutoring tool into university curricula for teaching heritage Russian in two countries – Finland and Kazakhstan. The traditions of teaching Russian in the two countries, while different in many respects, share an important feature: heritage learners of Russian represent a sizable proportion of all students – which needs to be addressed both pedagogically and technologically. The work is based on the language-learning system Revita (helsinki.fi/revita), which helps students learn languages by automatically creating exercises from arbitrary authentic text materials, chosen by the students or teachers.

Generative AI (GenAI) is being increasingly adopted in business, yet leveraging it effectively remains challenging due to diverse use cases and organizational needs. While generic end-user tools are widely used, they often fall short in addressing domain-specific tasks and integration requirements. This paper reviews the limitations of such tools and emphasizes the need for customized, use-case-specific GenAI solutions. We examine emerging software frameworks for developing tailored GenAI solutions.

We present polyNarrative, a new multilingual dataset of news articles, annotated for narratives. Narratives are overt or implicit claims, recurring across articles and languages, promoting a specific interpretation or viewpoint on an ongoing topic, often propagating mis/disinformation. We developed two-level taxonomies with coarse- and fine-grained narrative labels for two domains: (i) climate change and (ii) the military conflict between Ukraine and Russia. We collected news articles in four languages (Bulgarian, English, Portuguese, and Russian) related to the two domains and manually annotated them at the paragraph level. We make the dataset publicly available, along with experimental results of several strong baselines that assign narrative labels to news articles at the paragraph or the document level. We believe that this dataset will foster research in narrative detection and enable new research directions towards more multi-domain and highly granular narrative related tasks.

The remarkable capabilities of Large Language Models (LLMs) in text comprehension and generation have revolutionized Information Extraction (IE). One such advancement is in Document-level Relation Triplet Extraction (DocRTE), a critical task in information systems that aims to extract entities and their semantic relationships from documents. However, existing methods are primarily designed for Sentence level Relation Triplet Extraction (SentRTE), which typically handles a limited set of relations and triplet facts within a single sentence. Additionally, some approaches treat relations as candidate choices integrated into prompt templates, resulting in inefficient processing and suboptimal performance when determining the relation elements in triplets. To address these limitations, we introduce a Discriminative and Voice Aware Paradigm DiVA. DiVA involves only two steps: performing document-level relation extraction (DocRE) and then identifying the subject object entities based on the relation. No additional processing is required simply input the document to directly obtain the triplets. This streamlined process more accurately reflects real-world scenarios for triplet extraction. Our innovation lies in transforming DocRE into a discriminative task, where the model pays attention to each relation and to the often overlooked issue of active vs. passive voice within the triplet. Our experiments on the Re-DocRED and DocRED datasets demonstrate state-of-the-art results for the DocRTE task.

Assessment of proficiency of the learner is an essential part of Intelligent Tutoring Systems (ITS). We use Item Response Theory (IRT) in computer-aided language learning for assessment of student ability in two contexts: in test sessions, and in exercises during practice sessions. Exhaustive testing across a wide range of skills can provide a detailed picture of proficiency, but may be undesirable for a number of reasons. Therefore, we first aim to replace exhaustive tests with efficient but accurate adaptive tests. We use learner data collected from exhaustive tests under imperfect conditions, to train an IRT model to guide adaptive tests. Simulations and experiments with real learner data confirm that this approach is efficient and accurate. Second, we explore whether we can accurately estimate learner ability directly from the context of practice with exercises, without testing. We transform learner data collected from exercise sessions into a form that can be used for IRT modeling. This is done by linking the exercises to linguistic constructs; the constructs are then treated as "items" within IRT. We present results from large-scale studies with thousands of learners. Using teacher assessments of student ability as "ground truth," we compare the estimates obtained from tests vs. those from exercises. The experiments confirm that the IRT models can produce accurate ability estimation based on exercises.

This paper presents a corpus manually annotated with named entities for six Slavic languages - Bulgarian, Czech, Polish, Slovenian, Russian, and Ukrainian. This work is the result of a series of shared tasks, conducted in 2017-2023 as a part of the Workshops on Slavic Natural Language Processing. The corpus consists of 5 017 documents on seven topics. The documents are annotated with five classes of named entities. Each entity is described by a category, a lemma, and a unique cross-lingual identifier. We provide two train-tune dataset splits - single topic out and cross topics. For each split, we set benchmarks using a transformer-based neural network architecture with the pre-trained multilingual models - XLM-RoBERTa-large for named entity mention recognition and categorization, and mT5-large for named entity lemmatization and linking.