@inproceedings{yang-etal-2020-imec,
    title = "imec-{ETRO}-{VUB} at {W}-{NUT} 2020 Shared Task-3: A multilabel {BERT}-based system for predicting {COVID}-19 events",
    author = "Yang, Xiangyu  and
      Bekoulis, Giannis  and
      Deligiannis, Nikos",
    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/fix-sig-urls/2020.wnut-1.77/",
    doi = "10.18653/v1/2020.wnut-1.77",
    pages = "505--513",
    abstract = "In this paper, we present our system designed to address the W-NUT 2020 shared task for COVID-19 Event Extraction from Twitter. To mitigate the noisy nature of the Twitter stream, our system makes use of the COVID-Twitter-BERT (CT-BERT), which is a language model pre-trained on a large corpus of COVID-19 related Twitter messages. Our system is trained on the COVID-19 Twitter Event Corpus and is able to identify relevant text spans that answer pre-defined questions (i.e., slot types) for five COVID-19 related events (i.e., TESTED POSITIVE, TESTED NEGATIVE, CAN-NOT-TEST, DEATH and CURE {\&} PREVENTION). We have experimented with different architectures; our best performing model relies on a multilabel classifier on top of the CT-BERT model that jointly trains all the slot types for a single event. Our experimental results indicate that our Multilabel-CT-BERT system outperforms the baseline methods by 7 percentage points in terms of micro average F1 score. Our model ranked as 4th in the shared task leaderboard."
}