Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxic
This addresses the problem of fine-grained hate speech detection for online content moderation, but it is incremental as it builds on existing BERT methods with minor improvements.
The paper tackled the Toxic Spans Detection problem by proposing BERToxic, a system that fine-tunes BERT and uses post-processing steps, achieving an F1-score of 0.683 and placing 17th out of 91 teams.
This paper describes our approach to the Toxic Spans Detection problem (SemEval-2021 Task 5). We propose BERToxic, a system that fine-tunes a pre-trained BERT model to locate toxic text spans in a given text and utilizes additional post-processing steps to refine the boundaries. The post-processing steps involve (1) labeling character offsets between consecutive toxic tokens as toxic and (2) assigning a toxic label to words that have at least one token labeled as toxic. Through experiments, we show that these two post-processing steps improve the performance of our model by 4.16% on the test set. We also studied the effects of data augmentation and ensemble modeling strategies on our system. Our system significantly outperformed the provided baseline and achieved an F1-score of 0.683, placing Lone Pine in the 17th place out of 91 teams in the competition. Our code is made available at https://github.com/Yakoob-Khan/Toxic-Spans-Detection