The following system description presents our approach for detecting fake news in texts. The given task was formulated as a multi-class classification problem. Our approach is based on the combination of two BERT-based classification models: One model determines whether the textual content is relevant to the task; the second model assigns it a truth value. Starting from a pre-trained model for language representation, we fine-tuned these models on the given classification task in supervised training steps using the annotated data provided.    «

The following system description presents our approach for detecting fake news in texts. The given task was formulated as a multi-class classification problem. Our approach is based on the combination of two BERT-based classification models: One model determines whether the textual content is relevant to the task; the second model assigns it a truth value. Starting from a pre-trained model for language representation, we fine-tuned these models on the given classification task in supervised tra...    »