Approaching SMM4H with auto-regressive language models and back-translation
2021-06-01NAACL (SMM4H) 2021Unverified0· sign in to hype
Joseph Cornelius, Tilia Ellendorff, Fabio Rinaldi
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
We describe our submissions to the 6th edition of the Social Media Mining for Health Applications (SMM4H) shared task. Our team (OGNLP) participated in the sub-task: Classification of tweets self-reporting potential cases of COVID-19 (Task 5). For our submissions, we employed systems based on auto-regressive transformer models (XLNet) and back-translation for balancing the dataset.