@inproceedings{arkhipov-etal-2019-tuning,
    title = "Tuning Multilingual Transformers for Language-Specific Named Entity Recognition",
    author = "Arkhipov, Mikhail  and
      Trofimova, Maria  and
      Kuratov, Yuri  and
      Sorokin, Alexey",
    editor = "Erjavec, Toma{\v{z}}  and
      Marci{\'n}czuk, Micha{\l}  and
      Nakov, Preslav  and
      Piskorski, Jakub  and
      Pivovarova, Lidia  and
      {\v{S}}najder, Jan  and
      Steinberger, Josef  and
      Yangarber, Roman",
    booktitle = "Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing",
    month = aug,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/W19-3712/",
    doi = "10.18653/v1/W19-3712",
    pages = "89--93",
    abstract = "Our paper addresses the problem of multilingual named entity recognition on the material of 4 languages: Russian, Bulgarian, Czech and Polish. We solve this task using the BERT model. We use a hundred languages multilingual model as base for transfer to the mentioned Slavic languages. Unsupervised pre-training of the BERT model on these 4 languages allows to significantly outperform baseline neural approaches and multilingual BERT. Additional improvement is achieved by extending BERT with a word-level CRF layer. Our system was submitted to BSNLP 2019 Shared Task on Multilingual Named Entity Recognition and demonstrated top performance in multilingual setting for two competition metrics. We open-sourced NER models and BERT model pre-trained on the four Slavic languages."
}