@inproceedings{doan-bao-etal-2020-sunbear,
    title = "{S}un{B}ear at {WNUT}-2020 Task 2: Improving {BERT}-Based Noisy Text Classification with Knowledge of the Data domain",
    author = "Doan Bao, Linh  and
      Nguyen, Viet Anh  and
      Pham Huu, Quang",
    editor = "Xu, Wei  and
      Ritter, Alan  and
      Baldwin, Tim  and
      Rahimi, Afshin",
    booktitle = "Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.wnut-1.73/",
    doi = "10.18653/v1/2020.wnut-1.73",
    pages = "485--490",
    abstract = "This paper proposes an improved custom model for WNUT task 2: Identification of Informative COVID-19 English Tweet. We improve experiment with the effectiveness of fine-tuning methodologies for state-of-the-art language model RoBERTa. We make a preliminary instantiation of this formal model for the text classification approaches. With appropriate training techniques, our model is able to achieve 0.9218 F1-score on public validation set and the ensemble version settles at top 9 F1-score (0.9005) and top 2 Recall (0.9301) on private test set."
}