Kungfupanda at SemEval-2020 Task 12: BERT-Based Multi-Task Learning for Offensive Language Detection
This work addresses the problem of automatically detecting offensive content for social media moderation, but it is incremental as it builds on existing BERT and multi-task learning methods.
The paper tackled offensive language detection in social media by combining multi-task learning with BERT-based models, achieving a 91.51% F1 score in the OffensEval-2020 competition, which was close to the top score of 92.23%.
Nowadays, offensive content in social media has become a serious problem, and automatically detecting offensive language is an essential task. In this paper, we build an offensive language detection system, which combines multi-task learning with BERT-based models. Using a pre-trained language model such as BERT, we can effectively learn the representations for noisy text in social media. Besides, to boost the performance of offensive language detection, we leverage the supervision signals from other related tasks. In the OffensEval-2020 competition, our model achieves 91.51% F1 score in English Sub-task A, which is comparable to the first place (92.23%F1). An empirical analysis is provided to explain the effectiveness of our approaches.