Toxic Spans Detection(TSD) task is defined as highlighting spans that make a text toxic. Many works have been done to classify a given comment or document as toxic or non-toxic. However, none of those proposed models work at the token level. In this paper, we propose a self-attention-based bidirectional gated recurrent unit(BiGRU) with a multi-embedding representation of the tokens. Our proposed model enriches the representation by a combination of GPT-2, GloVe, and RoBERTa embeddings, which led to promising results. Experimental results show that our proposed approach is very effective in detecting span tokens.
@article{arxiv.2104.13164,
title = {UoT-UWF-PartAI at SemEval-2021 Task 5: Self Attention Based Bi-GRU with Multi-Embedding Representation for Toxicity Highlighter},
author = {Hamed Babaei Giglou and Taher Rahgooy and Mostafa Rahgouy and Jafar Razmara},
journal= {arXiv preprint arXiv:2104.13164},
year = {2021}
}
Comments
Accepted at SemEval-2021 Task 5: Toxic Spans Detection, ACL-IJCNLP 2021