@inproceedings{suppa-jariabka-2021-benchmarking,
    title = "Benchmarking Pre-trained Language Models for Multilingual {NER}: {T}ra{S}pa{S} at the {BSNLP}2021 Shared Task",
    author = "Suppa, Marek  and
      Jariabka, Ondrej",
    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-1.13/",
    pages = "105--114",
    abstract = "In this paper we describe TraSpaS, a submission to the third shared task on named entity recognition hosted as part of the Balto-Slavic Natural Language Processing (BSNLP) Workshop. In it we evaluate various pre-trained language models on the NER task using three open-source NLP toolkits: character level language model with Stanza, language-specific BERT-style models with SpaCy and Adapter-enabled XLM-R with Trankit. Our results show that the Trankit-based models outperformed those based on the other two toolkits, even when trained on smaller amounts of data. Our code is available at \url{https://github.com/NaiveNeuron/slavner-2021}."
}