Links
SICRIS
Prof. dr. Marko Robnik Šikonja
Full Professor
T: +386 1 479 8241
E:Send a message
Office hours: Wednesday, from 11:00 do 12:00 (2nd floor, right from the elevator). Please, contact me via email.
Room: R2.06 - Kabinet
Description

My research interests include artificial intelligence, machine learning, natural language processing, and network analytics. My focus is on large language models, deep neural networks, embeddings, explanation of models, ensemble learning, and feature evaluation. I am (co)author of more than 250 publications, both scientific and literary. My papers have more than 10,000 citations according to Google Scholar.
I tweet as @MarkoRobnikS and live in BlueSky as @markors.bsky.social 

Awards
  • Excellent in Science award (with coauthors) by the Slovenian Research and Innovation Agency ARIS in 2023
  • ECML/PKDD 2019 Journal Track Reviewer Award
  • The most outstanding research achievement of University of Ljubljana in 2018: Thesaurus of Modern Slovene: responsive dictionary (coauthor)
  • The golden medal for outstanding merits in the development of scientific, educational or artistic creation and to enhance the reputation of the University of Ljubljana (2015)

 

Classes
Laboratory
Projects
Past projects
Publications

  • ULČAR, Matej, ŽAGAR, Aleš, ARMENDARIZ, Carlos S., REPAR, Andraž, POLLAK, Senja, PURVER, Matthew, ROBNIK ŠIKONJA, Marko. Mono- and cross-lingual evaluation of representation language models on less-resourced languages. Computer speech & language. Jan. 2026, vol. 95, Article no. 101852, pp. 1-29, DOI: 10.1016/j.csl.2025.101852

  • YADAV, Anjali, GARG, Tanya, KLEMEN, Matej, ULČAR, Matej, AGARWAL, Basant, ROBNIK ŠIKONJA, Marko. From translation to generative LLMs: classification of code-mixed affective tasks. IEEE transactions on affective computing. 2025, DOI: 10.1109/TAFFC.2025.3553399

  • HOSTNIK, Marko, ROBNIK ŠIKONJA, Marko. Retrieval-augmented code completion for local projects using large language models. Expert systems with applications. Nov. 2025, vol. 292, article no. 128596, pp. 1-15, DOI: 10.1016/j.eswa.2025.128596

  • KOLOSKI, Boshko, ŠKRLJ, Blaž, ROBNIK ŠIKONJA, Marko, POLLAK, Senja. Measuring catastrophic forgetting in cross-lingual classification: transfer paradigms and tuning strategies. IEEE Access. 19 Feb. 2025, vol. 13, pp. 33509-33520, DOI: 10.1109/ACCESS.2025.3543608

  • VREŠ, Domen, ROBNIK ŠIKONJA, Marko. Preventing deception with explanation methods using focused sampling. Data mining and knowledge discovery. 2024, pp. 1-46, DOI: 10.1007/s10618-022-00900-w

  • MIOK, Kristian, HIDALGO TENORIO, Encarnación, OSENOVA, Petja, BENÍTEZ-CASTRO, Miguel-Ángel, ROBNIK ŠIKONJA, Marko. Multi-aspect multilingual and cross-lingual parliamentary speech analysis. Intelligent data analysis. Feb. 2024, vol. 28, no. 1, pp. 239-260, DOI: 10.3233/IDA-227347

  • VOUK, Boštjan, GUID, Matej, ROBNIK ŠIKONJA, Marko. Feature construction using explanations of individual predictions. Engineering applications of artificial intelligence, 2023, vol. 120, pp. 1-27, DOI: 10.1016/j.engappai.2023.105823

  • KLEMEN, Matej, KRSNIK, Luka, ROBNIK ŠIKONJA, Marko. Enhancing deep neural networks with morphological information. Natural language engineering. 2023, vol. 29, iss. 2, pp. 360-385, DOI: 10.1017/S1351324922000080

  • TRAJANOV, Dimitar, TRAJKOVSKI, Vangel, DIMITRIEVA, Makedonka, DOBREVA, Jovana, JOVANOVIK, Milos, KLEMEN, Matej, ŽAGAR, Aleš, ROBNIK ŠIKONJA, Marko. Review of natural language processing in pharmacology. Pharmacological reviews. Jul. 2023, vol. 75, no. 4, pp. 714-738. DOI

  • ŠKVORC, Tadej, GANTAR, Polona, ROBNIK ŠIKONJA, Marko. MICE: mining idioms with contextual embeddings. Knowledge-based systems. 2022, vol. 235, pp. 1-11, DOI: 10.1109/ACCESS.2022.3144932

  • Kristian Miok, Blaž Škrlj, Daniela Zaharie, Marko Robnik-Šikonja. To BAN or not to BAN: Bayesian Attention Networks for reliable hate speech detection. Cognitive Computation 2021. DOI

  • Matej Martinc, Senja Pollak, Marko Robnik-Šikonja. Supervised and unsupervised neural approaches to text readability. Computational linguistics. 47 (1): 141–179, 2021, DOI
  • Nada Lavrač, Blaž Škrlj, Marko Robnik-Šikonja. Propositionalization and embeddings: two sides of the same coin. Machine learning. 2020, 109(7):1465-1507. DOI
  • Jan Kralj, Marko Robnik-Šikonja, Nada Lavrač. NetSDM: semantic data mining with network analysis. Journal of machine learning research, 2019, vol. 20, pp. 1-50 PDF
  • Janez Kranjc, Roman Orač, Vid Podpečan, Nada Lavrač, Marko Robnik-Šikonja. ClowdFlows: online workflows for distributed big data mining. FGCS, 2017, vol. 68, pp. 38-58 PDF
  • Marko Bohanec, Mirjana Kljajić Borštnar, Marko Robnik-Šikonja. Explaining machine learning models in sales predictions. Expert systems with applications, 2017, vol. 71, pp. 416-428 PDF
  • Marko Robnik-Šikonja. Data generators for learning systems based on RBF networks. IEEE transactions on neural networks and learning systems, May 2016, vol. 27, no. 5, pp. 926-938 PDF
  • Marko Robnik-Šikonja, Igor Kononenko: Explaining Classifications For Individual Instances. IEEE Transactions on Knowledge and Data Engineering, 20: 589-600, 2008 PDF
  • Marko Robnik-Šikonja, Koen Vanhoof: Evaluation of ordinal attributes at value level. Knowledge Discovery and Data Mining, 14:225-243, 2007 PDF
  • Marko Robnik-Šikonja, Igor Kononenko: Theoretical and Empirical Analysis of ReliefF and RReliefF. Machine Learning Journal, 53:23-69, 2003. PDF
More