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- Anthology ID:
- 2021.semeval-1.132
- Volume:
- Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Venue:
- SemEval
- SIGs:
- SIGLEX | SIGSEM
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 967–973
- Language:
- URL:
- https://aclanthology.org/2021.semeval-1.132
- DOI:
- 10.18653/v1/2021.semeval-1.132
- Cite (ACL):
- Yakoob Khan, Weicheng Ma, and Soroush Vosoughi. 2021. Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxic. In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 967–973, Online. Association for Computational Linguistics.
- Cite (Informal):
- Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxic (Khan et al., SemEval 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.semeval-1.132.pdf
- Code
- Yakoob-Khan/Toxic-Spans-Detection
- Data
- HateXplain