Solomon at SemEval-2020 Task 11: Ensemble Architecture for Fine-Tuned Propaganda Detection in News Articles

TL;DR

This paper presents Solomon, an ensemble system using RoBERTa and specialized classifiers for propaganda technique detection in news articles, achieving 4th place in SemEval 2020 Task 11.

Contribution

The paper introduces an ensemble architecture combining RoBERTa fine-tuning with class-dependent classifiers and a dynamic LCS algorithm for improved propaganda technique classification.

Findings

Achieved 4th place in SemEval 2020 Task 11 leaderboard.

Demonstrated effectiveness of ensemble and specialized classifiers in propaganda detection.

Showed that dynamic LCS improves handling of repetition classes.

Abstract

This paper describes our system (Solomon) details and results of participation in the SemEval 2020 Task 11 "Detection of Propaganda Techniques in News Articles"\cite{DaSanMartinoSemeval20task11}. We participated in Task "Technique Classification" (TC) which is a multi-class classification task. To address the TC task, we used RoBERTa based transformer architecture for fine-tuning on the propaganda dataset. The predictions of RoBERTa were further fine-tuned by class-dependent-minority-class classifiers. A special classifier, which employs dynamically adapted Least Common Sub-sequence algorithm, is used to adapt to the intricacies of repetition class. Compared to the other participating systems, our submission is ranked 4th on the leaderboard.