Toxicity is pervasive in social media and poses a major threat to the health of online communities. The recent introduction of pre-trained language models, which have achieved state-of-the-art results in many NLP tasks, has transformed the way in which we approach natural language processing. However, the inherent nature of pre-training means that they are unlikely to capture task-specific statistical information or learn domain-specific knowledge. Additionally, most implementations of these models typically do not employ conditional random fields, a method for simultaneous token classification. We show that these modifications can improve model performance on the Toxic Spans Detection task at SemEval-2021 to achieve a score within 4 percentage points of the top performing team.
@article{arxiv.2110.03730,
title = {UoB at SemEval-2021 Task 5: Extending Pre-Trained Language Models to Include Task and Domain-Specific Information for Toxic Span Prediction},
author = {Erik Yan and Harish Tayyar Madabushi},
journal= {arXiv preprint arXiv:2110.03730},
year = {2021}
}
Comments
Published in Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021); Code available at: https://github.com/erikdyan/toxic_span_detection