UPB at SemEval-2021 Task 5: Virtual Adversarial Training for Toxic Spans Detection

Andrei Paraschiv, Dumitru-Clementin Cercel, Mihai Dascalu


Abstract
The real-world impact of polarization and toxicity in the online sphere marked the end of 2020 and the beginning of this year in a negative way. Semeval-2021, Task 5 - Toxic Spans Detection is based on a novel annotation of a subset of the Jigsaw Unintended Bias dataset and is the first language toxicity detection task dedicated to identifying the toxicity-level spans. For this task, participants had to automatically detect character spans in short comments that render the message as toxic. Our model considers applying Virtual Adversarial Training in a semi-supervised setting during the fine-tuning process of several Transformer-based models (i.e., BERT and RoBERTa), in combination with Conditional Random Fields. Our approach leads to performance improvements and more robust models, enabling us to achieve an F1-score of 65.73% in the official submission and an F1-score of 66.13% after further tuning during post-evaluation.
Anthology ID:
2021.semeval-1.26
Volume:
Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP | SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
225–232
Language:
URL:
https://aclanthology.org/2021.semeval-1.26
DOI:
10.18653/v1/2021.semeval-1.26
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.semeval-1.26.pdf