Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxic

TL;DR

This paper presents BERToxic, a fine-tuned BERT-based system with post-processing techniques for detecting toxic spans in text, achieving competitive results in SemEval-2021 Task 5.

Contribution

The paper introduces BERToxic with novel post-processing steps that improve toxic span detection performance over baselines.

Findings

Post-processing increases F1-score by 4.16%.

Achieved 0.683 F1-score, ranking 17th out of 91 teams.

Data augmentation and ensemble strategies further enhance results.

Abstract

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