LISAC FSDM USMBA at SemEval-2021 Task 5: Tackling Toxic Spans Detection Challenge with Supervised SpanBERT-based Model and Unsupervised LIME-based Model

Abdessamad Benlahbib, Ahmed Alami, Hamza Alami


Abstract
Toxic spans detection is an emerging challenge that aims to find toxic spans within a toxic text. In this paper, we describe our solutions to tackle toxic spans detection. The first solution, which follows a supervised approach, is based on SpanBERT model. This latter is intended to better embed and predict spans of text. The second solution, which adopts an unsupervised approach, combines linear support vector machine with the Local Interpretable Model-Agnostic Explanations (LIME). This last is used to interpret predictions of learning-based models. Our supervised model outperformed the unsupervised model and achieved the f-score of 67,84% (ranked 22/85) in Task 5 at SemEval-2021: Toxic Spans Detection.
Anthology ID:
2021.semeval-1.116
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:
865–869
Language:
URL:
https://aclanthology.org/2021.semeval-1.116
DOI:
10.18653/v1/2021.semeval-1.116
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.semeval-1.116.pdf
Optional supplementary material:
 2021.semeval-1.116.OptionalSupplementaryMaterial.zip