WMD at SemEval-2020 Tasks 7 and 11: Assessing humor and propaganda using Unsupervised Data Augmentation

摘要

In this work, we combine the state-of-the-art BERT architecture with the semi-supervised learning technique UDA in order to exploit unlabeled raw data to assess humor and detect propaganda in the tasks 7 and 11 of the SemEval-2020 competition. The use of UDA shows promising results with a systematic improvement of the performances over the four different subtasks, and even outperforms supervised learning with the additional labels of the Funlines dataset.