Abstract
Among the tasks motivated by the proliferation of misinformation, propaganda detection is particularly challenging due to the deficit of fine-grained manual annotations required to train machine learning models. Here we show how data from other related tasks, including credibility assessment, can be leveraged in multi-task learning (MTL) framework to accelerate the training process. To that end, we design a BERT-based model with multiple output layers, train it in several MTL scenarios and perform evaluation against the SemEval gold standard.- Anthology ID:
- 2021.semeval-1.141
- Volume:
- Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Alexis Palmer, Nathan Schneider, Natalie Schluter, Guy Emerson, Aurelie Herbelot, Xiaodan Zhu
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1027–1031
- Language:
- URL:
- https://aclanthology.org/2021.semeval-1.141
- DOI:
- 10.18653/v1/2021.semeval-1.141
- Cite (ACL):
- Konrad Kaczyński and Piotr Przybyła. 2021. HOMADOS at SemEval-2021 Task 6: Multi-Task Learning for Propaganda Detection. In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 1027–1031, Online. Association for Computational Linguistics.
- Cite (Informal):
- HOMADOS at SemEval-2021 Task 6: Multi-Task Learning for Propaganda Detection (Kaczyński & Przybyła, SemEval 2021)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2021.semeval-1.141.pdf