DUTH at SemEval-2020 Task 11: BERT with Entity Mapping for Propaganda Classification
This is an incremental improvement for NLP researchers working on propaganda detection in news.
The paper tackled propaganda technique classification in news articles by using BERT with entity mapping, achieving unspecified accuracy improvements through noise reduction and feature selection.
This report describes the methods employed by the Democritus University of Thrace (DUTH) team for participating in SemEval-2020 Task 11: Detection of Propaganda Techniques in News Articles. Our team dealt with Subtask 2: Technique Classification. We used shallow Natural Language Processing (NLP) preprocessing techniques to reduce the noise in the dataset, feature selection methods, and common supervised machine learning algorithms. Our final model is based on using the BERT system with entity mapping. To improve our model's accuracy, we mapped certain words into five distinct categories by employing word-classes and entity recognition.