@inproceedings{luo-etal-2021-ochadai,
    title = "{OCHADAI} at {SMM}4{H}-2021 Task 5: Classifying self-reporting tweets on potential cases of {COVID}-19 by ensembling pre-trained language models",
    author = "Luo, Ying  and
      Pereira, Lis  and
      Ichiro, Kobayashi",
    editor = "Magge, Arjun  and
      Klein, Ari  and
      Miranda-Escalada, Antonio  and
      Al-garadi, Mohammed Ali  and
      Alimova, Ilseyar  and
      Miftahutdinov, Zulfat  and
      Farre-Maduell, Eulalia  and
      Lopez, Salvador Lima  and
      Flores, Ivan  and
      O'Connor, Karen  and
      Weissenbacher, Davy  and
      Tutubalina, Elena  and
      Sarker, Abeed  and
      Banda, Juan M  and
      Krallinger, Martin  and
      Gonzalez-Hernandez, Graciela",
    booktitle = "Proceedings of the Sixth Social Media Mining for Health ({\#}SMM4H) Workshop and Shared Task",
    month = jun,
    year = "2021",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2021.smm4h-1.25/",
    doi = "10.18653/v1/2021.smm4h-1.25",
    pages = "123--125",
    abstract = {Since the outbreak of coronavirus at the end of 2019, there have been numerous studies on coro- navirus in the NLP arena. Meanwhile, Twitter has been a valuable source of news and a pub- lic medium for the conveyance of information and personal expression. This paper describes the system developed by the Ochadai team for the Social Media Mining for Health Appli- cations (SMM4H) 2021 Task 5, which aims to automatically distinguish English tweets that self-report potential cases of COVID-19 from those that do not. We proposed a model ensemble that leverages pre-trained represen- tations from COVID-Twitter-BERT (M{\"u}ller et al., 2020), RoBERTa (Liu et al., 2019), and Twitter-RoBERTa (Glazkova et al., 2021). Our model obtained F1-scores of 76{\%} on the test set in the evaluation phase, and 77.5{\%} in the post-evaluation phase.}
}