UPAppliedCL at GermEval 2021: Identifying Fact-Claiming and Engaging Facebook Comments Using Transformers

Robin Schaefer, Manfred Stede


Abstract
In this paper we present UPAppliedCL’s contribution to the GermEval 2021 Shared Task. In particular, we participated in Subtasks 2 (Engaging Comment Classification) and 3 (Fact-Claiming Comment Classification). While acceptable results can be obtained by using unigrams or linguistic features in combination with traditional machine learning models, we show that for both tasks transformer models trained on fine-tuned BERT embeddings yield best results.
Anthology ID:
2021.germeval-1.2
Volume:
Proceedings of the GermEval 2021 Shared Task on the Identification of Toxic, Engaging, and Fact-Claiming Comments
Month:
September
Year:
2021
Address:
Duesseldorf, Germany
Editors:
Julian Risch, Anke Stoll, Lena Wilms, Michael Wiegand
Venue:
GermEval
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13–18
Language:
URL:
https://aclanthology.org/2021.germeval-1.2
DOI:
Bibkey:
Cite (ACL):
Robin Schaefer and Manfred Stede. 2021. UPAppliedCL at GermEval 2021: Identifying Fact-Claiming and Engaging Facebook Comments Using Transformers. In Proceedings of the GermEval 2021 Shared Task on the Identification of Toxic, Engaging, and Fact-Claiming Comments, pages 13–18, Duesseldorf, Germany. Association for Computational Linguistics.
Cite (Informal):
UPAppliedCL at GermEval 2021: Identifying Fact-Claiming and Engaging Facebook Comments Using Transformers (Schaefer & Stede, GermEval 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.germeval-1.2.pdf