XD at SemEval-2020 Task 12: Ensemble Approach to Offensive Language Identification in Social Media Using Transformer Encoders
This work addresses the problem of detecting offensive content online for social media platforms, but it is incremental as it builds on existing transformer methods with an ensemble approach.
The paper tackled offensive language identification in social media by developing an ensemble model using transformer encoders, which achieved a macro-F1 of 90.9% on the test set and ranked among the top systems in a shared task with 85 participants.
This paper presents six document classification models using the latest transformer encoders and a high-performing ensemble model for a task of offensive language identification in social media. For the individual models, deep transformer layers are applied to perform multi-head attentions. For the ensemble model, the utterance representations taken from those individual models are concatenated and fed into a linear decoder to make the final decisions. Our ensemble model outperforms the individual models and shows up to 8.6% improvement over the individual models on the development set. On the test set, it achieves macro-F1 of 90.9% and becomes one of the high performing systems among 85 participants in the sub-task A of this shared task. Our analysis shows that although the ensemble model significantly improves the accuracy on the development set, the improvement is not as evident on the test set.