IITK@Detox at SemEval-2021 Task 5: Semi-Supervised Learning and Dice Loss for Toxic Spans Detection

Archit Bansal, Abhay Kaushik, Ashutosh Modi


Abstract
In this work, we present our approach and findings for SemEval-2021 Task 5 - Toxic Spans Detection. The task’s main aim was to identify spans to which a given text’s toxicity could be attributed. The task is challenging mainly due to two constraints: the small training dataset and imbalanced class distribution. Our paper investigates two techniques, semi-supervised learning and learning with Self-Adjusting Dice Loss, for tackling these challenges. Our submitted system (ranked ninth on the leader board) consisted of an ensemble of various pre-trained Transformer Language Models trained using either of the above-proposed techniques.
Anthology ID:
2021.semeval-1.24
Volume:
Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
Month:
August
Year:
2021
Address:
Online
Editors:
Alexis Palmer, Nathan Schneider, Natalie Schluter, Guy Emerson, Aurelie Herbelot, Xiaodan Zhu
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
211–219
Language:
URL:
https://aclanthology.org/2021.semeval-1.24
DOI:
10.18653/v1/2021.semeval-1.24
Bibkey:
Cite (ACL):
Archit Bansal, Abhay Kaushik, and Ashutosh Modi. 2021. IITK@Detox at SemEval-2021 Task 5: Semi-Supervised Learning and Dice Loss for Toxic Spans Detection. In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 211–219, Online. Association for Computational Linguistics.
Cite (Informal):
IITK@Detox at SemEval-2021 Task 5: Semi-Supervised Learning and Dice Loss for Toxic Spans Detection (Bansal et al., SemEval 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.semeval-1.24.pdf
Code
 architb1703/Toxic_Span
Data
Civil Comments