MUDES: Multilingual Detection of Offensive Spans

Tharindu Ranasinghe, Marcos Zampieri

Research output: Chapter in Book/Published conference outputConference publication

Abstract

The interest in offensive content identification in social media has grown substantially in recent years. Previous work has dealt mostly with post level annotations. However, identifying offensive spans is useful in many ways. To help coping with this important challenge, we present MUDES, a multilingual system to detect offensive spans in texts. MUDES features pre-trained models, a Python API for developers, and a user-friendly web-based interface. A detailed description of MUDES’ components is presented in this paper.
Original languageEnglish
Title of host publicationNAACL: North American Chapter of the Association for Computational Linguistics
PublisherAssociation for Computational Linguistics (ACL)
Pages144-152
Number of pages9
DOIs
Publication statusPublished - Jun 2021
Event2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Demonstrations - online
Duration: 6 Jun 202111 Jun 2021
https://2021.naacl.org/#:~:text=NAACL%2DHLT%202021%20is%20currently,6th%20to%20June%2011th%2C%202021.

Conference

Conference2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Demonstrations
Period6/06/2111/06/21
Internet address

Bibliographical note

ACL materials are Copyright © 1963–2023 ACL; Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License.

Fingerprint

Dive into the research topics of 'MUDES: Multilingual Detection of Offensive Spans'. Together they form a unique fingerprint.

Cite this