UIT-HSE at WNUT-2020 Task 2: Exploiting CT-BERT for Identifying COVID-19 Information on the Twitter Social Network

Recently, COVID-19 has affected a variety of real-life aspects of the world\nand led to dreadful consequences. More and more tweets about COVID-19 has been\nshared publicly on Twitter. However, the plurality of those Tweets are\nuninformative, which is challenging to build automatic systems to detect the\ninformative ones for useful AI applications. In this paper, we present our\nresults at the W-NUT 2020 Shared Task 2: Identification of Informative COVID-19\nEnglish Tweets. In particular, we propose our simple but effective approach\nusing the transformer-based models based on COVID-Twitter-BERT (CT-BERT) with\ndifferent fine-tuning techniques. As a result, we achieve the F1-Score of\n90.94\\% with the third place on the leaderboard of this task which attracted 56\nsubmitted teams in total.\n