Approaching SMM4H with auto-regressive language models and back-translation
Joseph Cornelius, Tilia Ellendorff, Fabio Rinaldi · 2021
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 autoregressive transformer models (XLNet) and back-translation for balancing the dataset.