@inproceedings{maveli-2020-edinburghnlp,
    title = "{E}dinburgh{NLP} at {WNUT}-2020 Task 2: Leveraging Transformers with Generalized Augmentation for Identifying Informativeness in {COVID}-19 Tweets",
    author = "Maveli, Nickil",
    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/ingest-emnlp/2020.wnut-1.67/",
    doi = "10.18653/v1/2020.wnut-1.67",
    pages = "455--461",
    abstract = "Twitter has become an important communication channel in times of emergency. The ubiquitousness of smartphones enables people to announce an emergency they{'}re observing in real-time. Because of this, more agencies are interested in programatically monitoring Twitter (disaster relief organizations and news agencies) and therefore recognizing the informativeness of a tweet can help filter noise from large volumes of data. In this paper, we present our submission for WNUT-2020 Task 2: Identification of informative COVID-19 English Tweets. Our most successful model is an ensemble of transformers including RoBERTa, XLNet, and BERTweet trained in a Semi-Supervised Learning (SSL) setting. The proposed system achieves a F1 score of 0.9011 on the test set (ranking 7th on the leaderboard), and shows significant gains in performance compared to a baseline system using fasttext embeddings."
}