Transfer Learning and Prediction Consistency for Detecting Offensive Spans of Text

Toxic span detection is the task of recognizing offensive spans in a text snippet. Although there has been prior work on classifying text snippets as offensive or not, the task of recognizing spans responsible for the toxicity of a text is not explored yet. In this work, we introduce a novel multi-task framework for toxic span detection in which the model seeks to simultaneously predict offensive words and opinion phrases to leverage their inter-dependencies and improve the performance. Moreover, we introduce a novel regularization mechanism to encourage the consistency of the model predictions across similar inputs for toxic span detection. Our extensive experiments demonstrate the effectiveness of the proposed model compared to strong baselines.