MedAI at SemEval-2021 Task 5: Start-to-end Tagging Framework for Toxic Spans Detection

Zhen Wang, Hongjie Fan, Junfei Liu


Abstract
This paper describes the system submitted to SemEval 2021 Task 5: Toxic Spans Detection. The task concerns evaluating systems that detect the spans that make a text toxic when detecting such spans are possible. To address the possibly multi-span detection problem, we develop a start-to-end tagging framework on top of RoBERTa based language model. Besides, we design a custom loss function that takes distance into account. In comparison to other participating teams, our system has achieved 69.03% F1 score, which is slightly lower (-1.8 and -1.73) than the top 1(70.83%) and top 2 (70.77%), respectively.
Anthology ID:
2021.semeval-1.30
Volume:
Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
Month:
August
Year:
2021
Address:
Online
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
258–262
Language:
URL:
https://aclanthology.org/2021.semeval-1.30
DOI:
10.18653/v1/2021.semeval-1.30
Bibkey:
Cite (ACL):
Zhen Wang, Hongjie Fan, and Junfei Liu. 2021. MedAI at SemEval-2021 Task 5: Start-to-end Tagging Framework for Toxic Spans Detection. In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 258–262, Online. Association for Computational Linguistics.
Cite (Informal):
MedAI at SemEval-2021 Task 5: Start-to-end Tagging Framework for Toxic Spans Detection (Wang et al., SemEval 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/remove-xml-comments/2021.semeval-1.30.pdf