Sefamerve ARGE at SemEval-2021 Task 5: Toxic Spans Detection Using Segmentation Based 1-D Convolutional Neural Network Model

Selman Delil, Birol Kuyumcu, Cüneyt Aksakallı


Abstract
This paper describes our contribution to SemEval-2021 Task 5: Toxic Spans Detection. Our approach considers toxic spans detection as a segmentation problem. The system, Waw-unet, consists of a 1-D convolutional neural network adopted from U-Net architecture commonly applied for semantic segmentation. We customize existing architecture by adding a special network block considering for text segmentation, as an essential component of the model. We compared the model with two transformers-based systems RoBERTa and XLM-RoBERTa to see its performance against pre-trained language models. We obtained 0.6251 f1 score with Waw-unet while 0.6390 and 0.6601 with the compared models respectively.
Anthology ID:
2021.semeval-1.123
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:
909–912
Language:
URL:
https://aclanthology.org/2021.semeval-1.123
DOI:
10.18653/v1/2021.semeval-1.123
Bibkey:
Cite (ACL):
Selman Delil, Birol Kuyumcu, and Cüneyt Aksakallı. 2021. Sefamerve ARGE at SemEval-2021 Task 5: Toxic Spans Detection Using Segmentation Based 1-D Convolutional Neural Network Model. In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 909–912, Online. Association for Computational Linguistics.
Cite (Informal):
Sefamerve ARGE at SemEval-2021 Task 5: Toxic Spans Detection Using Segmentation Based 1-D Convolutional Neural Network Model (Delil et al., SemEval 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.semeval-1.123.pdf
Code
 birolkuyumcu/wawunet_for_toxicspan