Muted: Multilingual Targeted Offensive Speech Identification and Visualization
This work addresses the need for more precise offensive speech detection and visualization in multiple languages, though it is incremental as it builds upon prior methods for span identification.
The authors tackled the problem of identifying offensive language spans and their targets in multilingual text by introducing Muted, a system that uses transformer-based models and attention heatmaps to visualize toxic content without additional fine-tuning, achieving performance on existing datasets and new German annotations.
Offensive language such as hate, abuse, and profanity (HAP) occurs in various content on the web. While previous work has mostly dealt with sentence level annotations, there have been a few recent attempts to identify offensive spans as well. We build upon this work and introduce Muted, a system to identify multilingual HAP content by displaying offensive arguments and their targets using heat maps to indicate their intensity. Muted can leverage any transformer-based HAP-classification model and its attention mechanism out-of-the-box to identify toxic spans, without further fine-tuning. In addition, we use the spaCy library to identify the specific targets and arguments for the words predicted by the attention heatmaps. We present the model's performance on identifying offensive spans and their targets in existing datasets and present new annotations on German text. Finally, we demonstrate our proposed visualization tool on multilingual inputs.