Abstract
In this paper we describe the methods we used for our submissions to the GermEval 2021 shared task on the identification of toxic, engaging, and fact-claiming comments. For all three subtasks we fine-tuned freely available transformer-based models from the Huggingface model hub. We evaluated the performance of various pre-trained models after fine-tuning on 80% of the training data with different hyperparameters and submitted predictions of the two best performing resulting models. We found that this approach worked best for subtask 3, for which we achieved an F1-score of 0.736.- Anthology ID:
- 2021.germeval-1.3
- 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:
- 19–24
- Language:
- URL:
- https://aclanthology.org/2021.germeval-1.3
- DOI:
- Cite (ACL):
- Christian Gawron and Sebastian Schmidt. 2021. FH-SWF SG at GermEval 2021: Using Transformer-Based Language Models to Identify Toxic, Engaging, & Fact-Claiming Comments. In Proceedings of the GermEval 2021 Shared Task on the Identification of Toxic, Engaging, and Fact-Claiming Comments, pages 19–24, Duesseldorf, Germany. Association for Computational Linguistics.
- Cite (Informal):
- FH-SWF SG at GermEval 2021: Using Transformer-Based Language Models to Identify Toxic, Engaging, & Fact-Claiming Comments (Gawron & Schmidt, GermEval 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2021.germeval-1.3.pdf