WLV-RIT at SemEval-2021 Task 5: A Neural Transformer Framework for Detecting Toxic Spans


In recent years, the widespread use of social media has led to an increase in the generation of toxic and offensive content on online platforms. In response, social media platforms have worked on developing automatic detection methods and employing human moderators to cope with this deluge of offensive content. While various state-of-the-art statistical models have been applied to detect toxic posts, there are only a few studies that focus on detecting the words or expressions that make a post offensive. This motivates the organization of the SemEval-2021 Task 5: Toxic Spans Detection competition, which has provided participants with a dataset containing toxic spans annotation in English posts. In this paper, we present the WLV-RIT entry for the SemEval-2021 Task 5. Our best performing neural transformer model achieves an 0.68 F1-Score. Furthermore, we develop an open-source framework for multilingual detection of offensive spans, i.e., MUDES, based on neural transformers that detect toxic spans in texts.

Publication DOI: https://doi.org/10.18653/v1/2021.semeval-1.111
Additional Information: ACL materials are Copyright © 1963–2023 ACL; other materials are copyrighted by their respective copyright holders. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License.
Event Title: 15th International Workshop on Semantic Evaluation (SemEval-2021)
Event Type: Other
Event Location: Online
Event Dates: 2022-08-05 - 2022-08-06
Last Modified: 11 Jan 2024 08:24
Date Deposited: 24 Jan 2023 16:20
Full Text Link: https://www.len ... 911-551-833-48X
https://aclanth ... .semeval-1.111/
Related URLs:
PURE Output Type: Conference contribution
Published Date: 2021-08
Authors: Ranasinghe, Tharindu (ORCID Profile 0000-0003-3207-3821)
Sarkar, Diptanu
Zampieri, Marcos
Ororbia, Alexander



Version: Published Version

License: Creative Commons Attribution

| Preview

Export / Share Citation


Additional statistics for this record