DUTH at SemEval-2020 Task 11: BERT with Entity Mapping for Propaganda Classification

Anastasios Bairaktaris, Symeon Symeonidis, Avi Arampatzis


Abstract
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
Anthology ID:
2020.semeval-1.227
Volume:
Proceedings of the Fourteenth Workshop on Semantic Evaluation
Month:
December
Year:
2020
Address:
Barcelona (online)
Editors:
Aurelie Herbelot, Xiaodan Zhu, Alexis Palmer, Nathan Schneider, Jonathan May, Ekaterina Shutova
Venue:
SemEval
SIG:
SIGLEX
Publisher:
International Committee for Computational Linguistics
Note:
Pages:
1732–1738
Language:
URL:
https://aclanthology.org/2020.semeval-1.227
DOI:
10.18653/v1/2020.semeval-1.227
Bibkey:
Cite (ACL):
Anastasios Bairaktaris, Symeon Symeonidis, and Avi Arampatzis. 2020. DUTH at SemEval-2020 Task 11: BERT with Entity Mapping for Propaganda Classification. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 1732–1738, Barcelona (online). International Committee for Computational Linguistics.
Cite (Informal):
DUTH at SemEval-2020 Task 11: BERT with Entity Mapping for Propaganda Classification (Bairaktaris et al., SemEval 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.semeval-1.227.pdf
Code
 anasbair/SemEval2020-groups