@inproceedings{kurfali-2020-travis,
    title = "{TRAVIS} at {PARSEME} Shared Task 2020: How good is (m){BERT} at seeing the unseen?",
    author = "Kurfal{\i}, Murathan",
    editor = "Markantonatou, Stella  and
      McCrae, John  and
      Mitrovi{\'c}, Jelena  and
      Tiberius, Carole  and
      Ramisch, Carlos  and
      Vaidya, Ashwini  and
      Osenova, Petya  and
      Savary, Agata",
    booktitle = "Proceedings of the Joint Workshop on Multiword Expressions and Electronic Lexicons",
    month = dec,
    year = "2020",
    address = "online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Add-Cong-Liu-Florida-Atlantic-University-author-id/2020.mwe-1.18/",
    pages = "136--141",
    abstract = "This paper describes the TRAVIS system built for the PARSEME Shared Task 2020 on semi-supervised identification of verbal multiword expressions. TRAVIS is a fully feature-independent model, relying only on the contextual embeddings. We have participated with two variants of TRAVIS, TRAVIS-multi and TRAVIS-mono, where the former employs multilingual contextual embeddings and the latter uses monolingual ones. Our systems are ranked second and third among seven submissions in the open track, respectively. Despite the strong performance of multilingual contextual embeddings across all languages, the results show that language-specific contextual embeddings have better generalization capabilities."
}