Nikola Ljubešić


  • basic linguistic processing of South Slavic languages
  • linguistic processing of non-standard language
  • data harvesting for self-supervised representation learning
  • computational social science
  • hate speech detection



  • FIŠER, Darja, LJUBEŠIĆ, Nikola, ERJAVEC, Tomaž. The Janes project : language resources and tools for Slovene user generated content. Language resources and evaluation. 2020, vol. 54, no. 1, str. 223-246, ilustr. ISSN 1574-020X. DOI: 10.1007/s10579-018-9425-z. [COBISS.SI-ID 68029026]
  • LJUBEŠIĆ, Nikola, MILIČEVIĆ, Maja, SAMARDŽIĆ, Tanja. Borders and boundaries in Bosnian, Croatian, Montenegrin and Serbian : Twitter data to the rescue. Journal of linguistic geography. 2019, vol. 6, no. 2, str. 100-124. ISSN 2049-7547. DOI: 10.1017/jlg.2018.9. [COBISS.SI-ID 32783655]
  • ZUPAN, Katja, LJUBEŠIĆ, Nikola, ERJAVEC, Tomaž. How to tag non-standard language : normalisation versus domain adaptation for Slovene historical and user-generated texts. Natural language engineering. 2019, vol. 25, spec. iss. 5, str. 651-674. ISSN 1351-3249. DOI: 10.1017/S1351324919000366. [COBISS.SI-ID 32634151]
  • GOOT, Ron van der, LJUBEŠIĆ, Nikola, MATROOS, Ian, NISSIM, Malvina, PLANK, Barbara. Bleaching text : abstract features for cross-lingual gender prediction : Rob van der Goot … [et al.]. V: The 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, July 15 – 20, 2018, Melbourne, Australia. Stroudsburg: Association for Computational Linguistics, 2018. Str. 383-389. Proceedings of the conference, vol. 2. ISBN 978-1-948087-34-6. [COBISS.SI-ID 32812839]