SUJT | Research

Our projects

LAHTEX - Slovene Easy-to-Read Corpus for Text Simplification Using Artificial Intelligence

CATEGORY

10 Feb, 2026

LAHTEX - Slovene Easy-to-Read Corpus for Text Simplification Using Artificial Intelligence

The primary objective of the project is therefore the creation of the first easy-to-read corpus in Slovene, which will enable empirical research into easy-to-read Slovene and support the development of artificial intelligence tools for text simplification.

LLM4DH - Large Language Models for Digital Humanities

CATEGORY

10 Feb, 2026

LLM4DH - Large Language Models for Digital Humanities

The project will improve the technology of large language models with different data and knowledge, reduce the computational complexity of speech technologies, and give them access to reliable external information. Improvements in the core capabilities of large language models will lead to breakthroughs in several areas of the digital humanities: linguistics and lexicography, education, analysis of social phenomena and contemporary history, folkloristics, and law.

PoVeJMo – Adaptive Natural Language Processing with the Help of Large Language Models

CATEGORY

10 Feb, 2026

PoVeJMo – Adaptive Natural Language Processing with the Help of Large Language Models

In this project, we will develop several efficient open-source language models. The constructed model will be the first of its kind for a morphologically rich low-resource language.

SMASH – Machine Learning for Science and the Humanities

CATEGORY

9 Feb, 2026

SMASH – Machine Learning for Science and the Humanities

SMASH is an innovative, cross-sectoral training program for career development, co-funded under the Marie Skłodowska-Curie COFUND (MSCA COFUND) calls for the period 2023–2028. The goal of the SMASH program is to enhance research excellence and career prospects of outstanding postdoctoral researchers from around the world.

Centre of Excellence in AI for Digital Humanities (AI4DH)

CATEGORY

8 Feb, 2026

Centre of Excellence in AI for Digital Humanities (AI4DH)

LLMs4EU Large Language Models for European Union

CATEGORY

8 Feb, 2026

LLMs4EU Large Language Models for European Union

Practical quantum advantage of reservoir computing on NISQ devices

CATEGORY

8 Feb, 2026

Practical quantum advantage of reservoir computing on NISQ devices

This project explores quantum reservoir computing on current quantum devices through experiments, theory, and simulations.

CATEGORY

8 Feb, 2026

SLAIF - Slovenian AI Factory

The Slovenian AI Factory will provide comprehensive AI and supercomputing solutions for research, public administration and business, bolstering innovation and European digital sovereignty.

STRATIFYHF – Decision Support System Based on Artificial Intelligence

CATEGORY

8 Feb, 2026

STRATIFYHF – Decision Support System Based on Artificial Intelligence

The STRATIFYHF project will transform the way heart failure is diagnosed today, thereby improving patients’ quality and length of life and leading to efficient and sustainable healthcare systems by reducing hospital admissions related to heart failure and unnecessary referrals from primary to secondary care across Europe and beyond.

Vector embedding techniques for media applications

CATEGORY

8 Feb, 2026

Vector embedding techniques for media applications

In this application project in collaboration with Kliping, d.o.o. we are developing advanced multilingual tools for analysing news and social media content that will help automate these processes while increasing society’s ability to understand the rapid flow of available information.

Publications

Clinical validation of an artificial intelligence-based decision support system for diagnosis and risk stratification of heart failure

CATEGORY

4 Feb, 2026

Clinical validation of an artificial intelligence-based decision support system for diagnosis and risk stratification of heart failure

The primary aim of the present study is to collect prospective clinical data to validate the STRATIFYHF DSS (in terms of diagnostic accuracy, sensitivity and specificity) as a tool to predict the risk, diagnosis and progression of HF. The secondary outcomes are the demographic and clinical predictors of risk, diagnosis and progression of HF.

CroSloMet: A Structured Metaphor Dataset for Croatian and Slovene

CATEGORY

4 Feb, 2026

CroSloMet: A Structured Metaphor Dataset for Croatian and Slovene

In this paper, we present CroSloMet, a novel dataset of over 1,120 metaphorical and 1,120 literal sentences in Croatian and Slovene, grounded in the MetaNet.HR framework. Each example is annotated with the corresponding conceptual metaphor, linguistic multi-word expression (MWE), canonical forms, and literal usage, enabling both metaphor identification and explanation tasks.

Mono- and cross-lingual evaluation of representation language models on less-resourced languages

CATEGORY

4 Feb, 2026

Mono- and cross-lingual evaluation of representation language models on less-resourced languages

We present a large-scale multilingual empirical comparison of several monolingual and multilingual ELMo and BERT models using 14 classification tasks in nine languages.