FH-SWF SG at GermEval 2021: Using Transformer-Based Language Models to Identify Toxic, Engaging, & Fact-Claiming Comments
This work addresses the challenge of content moderation in German online platforms, but it is incremental as it applies existing methods to a new dataset.
The paper tackled the problem of identifying toxic, engaging, and fact-claiming comments in German text by fine-tuning transformer-based models, achieving an F1-score of 0.736 for the fact-claiming subtask.
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.