S-NLP at SemEval-2021 Task 5: An Analysis of Dual Networks for Sequence Tagging

Viet Anh Nguyen, Tam Minh Nguyen, Huy Quang Dao, Quang Huu Pham


Abstract
The SemEval 2021 task 5: Toxic Spans Detection is a task of identifying considered-toxic spans in text, which provides a valuable, automatic tool for moderating online contents. This paper represents the second-place method for the task, an ensemble of two approaches. While one approach relies on combining different embedding methods to extract diverse semantic and syntactic representations of words in context; the other utilizes extra data with a slightly customized Self-training, a semi-supervised learning technique, for sequence tagging problems. Both of our architectures take advantage of a strong language model, which was fine-tuned on a toxic classification task. Although experimental evidence indicates higher effectiveness of the first approach than the second one, combining them leads to our best results of 70.77 F1-score on the test dataset.
Anthology ID:
2021.semeval-1.120
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:
888–897
Language:
URL:
https://aclanthology.org/2021.semeval-1.120
DOI:
10.18653/v1/2021.semeval-1.120
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.semeval-1.120.pdf