@inproceedings{perrio-tayyar-madabushi-2020-cxp949,
    title = "{CXP}949 at {WNUT}-2020 Task 2: Extracting Informative {COVID}-19 Tweets - {R}o{BERT}a Ensembles and The Continued Relevance of Handcrafted Features",
    author = "Perrio, Calum  and
      Tayyar Madabushi, Harish",
    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-1.48/",
    doi = "10.18653/v1/2020.wnut-1.48",
    pages = "352--358",
    abstract = "This paper presents our submission to Task 2 of the Workshop on Noisy User-generated Text. We explore improving the performance of a pre-trained transformer-based language model fine-tuned for text classification through an ensemble implementation that makes use of corpus level information and a handcrafted feature. We test the effectiveness of including the aforementioned features in accommodating the challenges of a noisy data set centred on a specific subject outside the remit of the pre-training data. We show that inclusion of additional features can improve classification results and achieve a score within 2 points of the top performing team."
}