MUDES: Multilingual Detection of Offensive Spans
This addresses the need for more granular offensive content detection in social media across multiple languages, but it appears incremental as it builds on existing work in offensive content identification.
The paper tackles the problem of identifying offensive content at the span level in multilingual texts, presenting MUDES, a system that includes pre-trained models, a Python API, and a web interface.
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.