AStarTwice at SemEval-2021 Task 5: Toxic Span Detection Using RoBERTa-CRF, Domain Specific Pre-Training and Self-Training

Thakur Ashutosh Suman, Abhinav Jain


Abstract
This paper describes our contribution to SemEval-2021 Task 5: Toxic Spans Detection. Our solution is built upon RoBERTa language model and Conditional Random Fields (CRF). We pre-trained RoBERTa on Civil Comments dataset, enabling it to create better contextual representation for this task. We also employed the semi-supervised learning technique of self-training, which allowed us to extend our training dataset. In addition to these, we also identified some pre-processing steps that significantly improved our F1 score. Our proposed system achieved a rank of 41 with an F1 score of 66.16%.
Anthology ID:
2021.semeval-1.118
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:
875–880
Language:
URL:
https://aclanthology.org/2021.semeval-1.118
DOI:
10.18653/v1/2021.semeval-1.118
Bibkey:
Cite (ACL):
Thakur Ashutosh Suman and Abhinav Jain. 2021. AStarTwice at SemEval-2021 Task 5: Toxic Span Detection Using RoBERTa-CRF, Domain Specific Pre-Training and Self-Training. In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 875–880, Online. Association for Computational Linguistics.
Cite (Informal):
AStarTwice at SemEval-2021 Task 5: Toxic Span Detection Using RoBERTa-CRF, Domain Specific Pre-Training and Self-Training (Suman & Jain, SemEval 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2021.semeval-1.118.pdf