newsSweeper at SemEval-2020 Task 11: Context-Aware Rich Feature Representations For Propaganda Classification
This work addresses the challenge of identifying propaganda in news for media analysis, but it is incremental as it builds on existing pre-trained models and tagging techniques.
The paper tackled the problem of detecting propaganda techniques in news articles by developing a system using BERT and RoBERTa models enhanced with tagging and contextual features, achieving a 5th-place ranking in the technique classification subtask.
This paper describes our submissions to SemEval 2020 Task 11: Detection of Propaganda Techniques in News Articles for each of the two subtasks of Span Identification and Technique Classification. We make use of pre-trained BERT language model enhanced with tagging techniques developed for the task of Named Entity Recognition (NER), to develop a system for identifying propaganda spans in the text. For the second subtask, we incorporate contextual features in a pre-trained RoBERTa model for the classification of propaganda techniques. We were ranked 5th in the propaganda technique classification subtask.