@inproceedings{ljubesic-lauc-2021-bertic,
    title = "{BERT}i{\'c} - The Transformer Language Model for {B}osnian, {C}roatian, {M}ontenegrin and {S}erbian",
    author = "Ljube{\v{s}}i{\'c}, Nikola  and
      Lauc, Davor",
    editor = "Babych, Bogdan  and
      Kanishcheva, Olga  and
      Nakov, Preslav  and
      Piskorski, Jakub  and
      Pivovarova, Lidia  and
      Starko, Vasyl  and
      Steinberger, Josef  and
      Yangarber, Roman  and
      Marci{\'n}czuk, Micha{\l}  and
      Pollak, Senja  and
      P{\v{r}}ib{\'a}{\v{n}}, Pavel  and
      Robnik-{\v{S}}ikonja, Marko",
    booktitle = "Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing",
    month = apr,
    year = "2021",
    address = "Kiyv, Ukraine",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2021.bsnlp-1.5/",
    pages = "37--42",
    abstract = "In this paper we describe a transformer model pre-trained on 8 billion tokens of crawled text from the Croatian, Bosnian, Serbian and Montenegrin web domains. We evaluate the transformer model on the tasks of part-of-speech tagging, named-entity-recognition, geo-location prediction and commonsense causal reasoning, showing improvements on all tasks over state-of-the-art models. For commonsense reasoning evaluation we introduce COPA-HR - a translation of the Choice of Plausible Alternatives (COPA) dataset into Croatian. The BERTi{\'c} model is made available for free usage and further task-specific fine-tuning through HuggingFace."
}