arjunth2001 / germeval-2021 Goto Github PK
View Code? Open in Web Editor NEWCodes for our submission for the sub-tasks of the Germeval 2021 shared task on the Identification of Toxic, Engaging, and Fact-Claiming Comments. The system we use is an ensemble of state-of-the-art pretrained models finetuned with engineered features. We show how feature engineering and data augmentation can be helpful when training data is less.