@inproceedings{prelevikj-zitnik-2021-multilingual,
    title = "Multilingual Named Entity Recognition and Matching Using {BERT} and Dedupe for {S}lavic Languages",
    author = "Prelevikj, Marko  and
      Zitnik, Slavko",
    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-1.9/",
    pages = "80--85",
    abstract = "This paper describes the University of Ljubljana (UL FRI) Group{'}s submissions to the shared task at the Balto-Slavic Natural Language Processing (BSNLP) 2021 Workshop. We experiment with multiple BERT-based models, pre-trained in multi-lingual, Croatian-Slovene-English and Slovene-only data. We perform training iteratively and on the concatenated data of previously available NER datasets. For the normalization task we use Stanza lemmatizer, while for entity matching we implemented a baseline using the Dedupe library. The performance of evaluations suggests that multi-source settings outperform less-resourced approaches. The best NER models achieve 0.91 F-score on Slovene training data splits while the best official submission achieved F-scores of 0.84 and 0.78 for relaxed partial matching and strict settings, respectively. In multi-lingual NER setting we achieve F-scores of 0.82 and 0.74."
}