29 papers

Publications

Journal articles & conference papers, grouped by year.

2026
2 papers
First page of “Extracting Biomedical Entities from Clinical Records: A Comparative Study of Large Language Model Approaches”
Selected · Journal
Extracting Biomedical Entities from Clinical Records: A Comparative Study of Large Language Model Approaches
E. Calcina, E. Novak, D. Mladenić, PREPARE Project Group · Applied Artificial Intelligence, 40(1) · 2026 · DOI ·
Compares large language model approaches for extracting biomedical entities from multilingual clinical records within the PREPARE project.
First page of “An Iterative Annotation Pipeline for Building Clinical Datasets and Training Information Extraction Models: The PREPARE Project”
Conference
An Iterative Annotation Pipeline for Building Clinical Datasets and Training Information Extraction Models: The PREPARE Project
E. Calcina, E. Novak, L. Pepa, M. G. Ceravolo, the PREPARE Project Group · 7th European OHDSI Symposium (poster), Rotterdam · 2026 · PDF ·
2025
4 papers
First page of “Evaluating Open-Source Large Language Models for Synthetic Non-English Medical Data Generation Using Prompt-Based Techniques”
First page of “Semantic Prompting for Large Language Models in Biomedical Named Entity Recognition”
Conference
Semantic Prompting for Large Language Models in Biomedical Named Entity Recognition
E. Calcina, E. Novak, D. Mladenić · Proceedings of the Slovenian Conference on Data Mining and Data Warehouses (SiKDD 2025), Ljubljana · 2025 · PDF ·
First page of “An Iterative LLM-based Pipeline for Extracting Clinical Data from Medical Records”
Conference
An Iterative LLM-based Pipeline for Extracting Clinical Data from Medical Records
E. Calcina, T. Meterc, N. Shpanko, L. Spindari, E. Lindner, L. Hoogendam, H. Slijper, R. Selles, E. Novak · OHDSI Europe Symposium (poster), Hasselt · 2025 ·
First page of “The 2021 Tokyo Olympics Multilingual News Article Dataset”
arXiv
The 2021 Tokyo Olympics Multilingual News Article Dataset
E. Novak, E. Calcina, D. Mladenić, M. Grobelnik · arXiv:2502.06648 · 2025 · DOI ·
2024
8 papers
First page of “Evaluating Text Generation Model Performance by Combining Semantic Meaning and Word Order”
Selected · Journal
Evaluating Text Generation Model Performance by Combining Semantic Meaning and Word Order
E. Novak, L. Bizjak, D. Mladenić, M. Grobelnik · IEEE Access, 12 · 2024 · DOI ·
An evaluation metric for text generation that couples semantic similarity with word-order sensitivity, outperforming BLEU-style baselines.
First page of “TARNet for the Classification of Time Series with Missing Values: A Strong Baseline”
Journal
TARNet for the Classification of Time Series with Missing Values: A Strong Baseline
K. Buza, E. Novak · Acta Universitatis Sapientiae, Informatica, 16(1) · 2024 · DOI ·
First page of “Exploring Kleefstra Syndrome Cohort Phenotype Characteristics: Prevalence Insights from Caregiver-Reported Outcomes”
Journal
Exploring Kleefstra Syndrome Cohort Phenotype Characteristics: Prevalence Insights from Caregiver-Reported Outcomes
T. Zdolšek Draksler, A. Bouman, A. Guček, E. Novak, P. Burger, F. Colin, T. Kleefstra · European Journal of Medical Genetics, 72 · 2024 · DOI ·
First page of “Generating Non-English Synthetic Medical Data Sets”
Conference
Generating Non-English Synthetic Medical Data Sets
L. Dolinar, E. Calcina, E. Novak · Proceedings of the Slovenian Conference on Data Mining and Data Warehouses (SiKDD 2024), Ljubljana · 2024 · DOI · PDF ·
First page of “Creating Local World Models using LLMs”
Conference
Creating Local World Models using LLMs
M. D. Longar, E. Novak, M. Grobelnik · Proceedings of the Slovenian Conference on Data Mining and Data Warehouses (SiKDD 2024), Ljubljana · 2024 · DOI · PDF ·
First page of “Knowledge graph Extraction from Textual data using LLM”
Conference
Knowledge graph Extraction from Textual data using LLM
K. Gillani, K. Kenda, E. Novak, D. Mladenić · Proceedings of the Slovenian Conference on Data Mining and Data Warehouses (SiKDD 2024), Ljubljana · 2024 · DOI · PDF ·
Dataset
The news articles reporting on the 2021 Tokyo Olympics data set OG2021 (public)
E. Novak, E. Calcina, D. Mladenić, M. Grobelnik · CLARIN.SI repository · 2024 ·
Dataset
The news articles reporting on the 2021 Tokyo Olympics data set OG2021 (research)
E. Novak, E. Calcina, D. Mladenić, M. Grobelnik · CLARIN.SI repository · 2024 ·
2023
1 paper
Dataset
Open Slovene WordNet OSWN 1.0
J. Čibej, L. Terčon, S. Krek, A. Repar, E. Novak, P. Gantar, I. Kosem, Š. Arhar Holdt, K. Dobrovoljc, A. Berginc, I. Hvala, D. Klement, M. Kolenc, A. Močnik, T. Munda, D. Pavlas, A. Pečan, A. Poljak, D. Sečnik, J. Šešet, J. Štumberger, T. Toličič, L. Trpin · CLARIN.SI repository · 2023 ·
2022
6 papers
First page of “Why is a Document Relevant? Understanding the Relevance Scores in Cross-Lingual Document Retrieval”
Selected · Journal
Why is a Document Relevant? Understanding the Relevance Scores in Cross-Lingual Document Retrieval
E. Novak, L. Bizjak, D. Mladenić, M. Grobelnik · Knowledge-Based Systems, 244 · 2022 · DOI ·
Examines what drives the relevance scores in cross-lingual document retrieval, making multilingual ranking models interpretable.
First page of “SLOmet - Slovenian Commonsense Description”
Conference
SLOmet - Slovenian Commonsense Description
A. Mladenić Grobelnik, E. Novak, D. Mladenić, M. Grobelnik · Proceedings of the Slovenian Conference on Data Mining and Data Warehouses (SiKDD 2022), Ljubljana · 2022 · PDF ·
First page of “Measuring the Similarity of Song Artists using Topic Modelling”
Conference
Measuring the Similarity of Song Artists using Topic Modelling
E. Calcina, E. Novak · Proceedings of the Slovenian Conference on Data Mining and Data Warehouses (SiKDD 2022), Ljubljana · 2022 · PDF ·
First page of “Automatically Generating Text from Film Material - A Comparison of Three Models”
Conference
Automatically Generating Text from Film Material - A Comparison of Three Models
S. Korenič Tratnik, E. Novak · Proceedings of the Slovenian Conference on Data Mining and Data Warehouses (SiKDD 2022), Ljubljana · 2022 · PDF ·
First page of “Screening Tool for Anti-money Laundering Supervision”
Conference
Screening Tool for Anti-money Laundering Supervision
F. Koprivec, G. Kržmanc, M. Škrjanc, K. Kenda, E. Novak · Big Data and Artificial Intelligence in Digital Finance · 2022 · DOI ·
Dataset
Slovene Translation of the ATOMIC 2020 data set SloATOMIC 2020
A. Mladenić Grobelnik, E. Novak, D. Mladenić, M. Grobelnik · CLARIN.SI repository · 2022 ·
2021
3 papers
First page of “News Stream Clustering using Multilingual Language Models”
Conference
News Stream Clustering using Multilingual Language Models
E. Novak · Proceedings of the Slovenian Conference on Data Mining and Data Warehouses (SiKDD 2021), Ljubljana · 2021 · PDF ·
First page of “An AI-based Learning Companion Promoting Lifelong Learning Opportunities for All”
arXiv
An AI-based Learning Companion Promoting Lifelong Learning Opportunities for All
M. Perez-Ortiz, E. Novak, S. Bulathwela, J. Shawe-Taylor · arXiv:2112.01242 · 2021 · DOI ·
First page of “PEEK: A Large Dataset of Learner Engagement with Educational Videos”
arXiv
PEEK: A Large Dataset of Learner Engagement with Educational Videos
S. Bulathwela, M. Perez-Ortiz, E. Novak, E. Yilmaz, J. Shawe-Taylor · arXiv:2109.03154 · 2021 · DOI ·
2020
1 paper
First page of “Users' Learning Pathways on Cross-site Open Educational Resources”
Conference
Users' Learning Pathways on Cross-site Open Educational Resources
A. S. Sunar, E. Novak, D. Mladenić · Proceedings of the 12th International Conference on Computer Supported Education - Volume 2: CSEDU · 2020 · DOI ·
2019
4 papers
First page of “Streaming Data Fusion for the Internet of Things”
Selected · Journal
Streaming Data Fusion for the Internet of Things
K. Kenda, B. Kažič, E. Novak, D. Mladenić · Sensors, 19(8) · 2019 · DOI ·
A streaming data fusion methodology that turns heterogeneous IoT sensor streams into feature vectors ready for machine learning.
First page of “Semantic Enrichment and Analysis of Legal Domain Documents”
Conference
Semantic Enrichment and Analysis of Legal Domain Documents
M. B. Massri, S. Brezec, E. Novak, K. Kenda · Proceedings of the Slovenian Conference on Data Mining and Data Warehouses (SiKDD 2019), Ljubljana · 2019 · PDF ·
First page of “Document Embedding Models on Environmental Legal Documents”
Conference
Document Embedding Models on Environmental Legal Documents
S. Kralj, Ž. Urbančič, E. Novak, K. Kenda · Proceedings of the Slovenian Conference on Data Mining and Data Warehouses (SiKDD 2019), Ljubljana · 2019 · PDF ·
First page of “Preferences of Users on Cross-Site OER Recommendations: Stay or Leave?”
Conference
Preferences of Users on Cross-Site OER Recommendations: Stay or Leave?
A. S. Sunar, E. Novak, J. Urbančič, D. Mladenić · Proceedings of the Slovenian Conference on Data Mining and Data Warehouses (SiKDD 2019), Ljubljana · 2019 · PDF ·
2018
1 paper
First page of “Preparing Multi-Modal Data for Natural Language Processing”
Conference
Preparing Multi-Modal Data for Natural Language Processing
E. Novak, J. Urbančič, M. Jenko · Proceedings of the Slovenian Conference on Data Mining and Data Warehouses (SiKDD 2018), Ljubljana · 2018 · PDF ·
2017
1 paper
First page of “Connecting Professional Skill Demand with Supply”
Conference
Connecting Professional Skill Demand with Supply
E. Novak, I. Novalija · Proceedings of the Slovenian Conference on Data Mining and Data Warehouses (SiKDD 2017), Ljubljana · 2017 · PDF ·
2016
1 paper
First page of “Visual and Statistical Analysis of VideoLectures.NET”
Conference
Visual and Statistical Analysis of VideoLectures.NET
E. Novak, I. Novalija · Proceedings of the Slovenian Conference on Data Mining and Data Warehouses (SiKDD 2016), Ljubljana · 2016 · PDF ·
2014
1 paper
First page of “QMiner: Data Analytics Platform for Processing Streams of Structured and Unstructured Data”
Conference
QMiner: Data Analytics Platform for Processing Streams of Structured and Unstructured Data
B. Fortuna, J. Rupnik, J. Brank, C. Fortuna, V. Jovanoski, M. Karlovčec, B. Kažič, K. Kenda, G. Leban, A. Muhič, E. Novak, J. Novljan, M. Papler, L. Rei, B. Sovdat, L. Stopar, M. Grobelnik, D. Mladenić · Workshop on Software Engineering for Machine Learning, NeurIPS · 2014 ·