AbstractRecognizing offensive text is an important requirement for every content management system, especially for social networks. While the majority of the prior work formulate this problem as text classification, i.e., if a text excerpt is offensive or not, in this work we propose a novel model for offensive span detection (OSD), whose goal is to identify the spans responsible for the offensive tone of the text. One of the challenges to train a model for this novel setting is the lack of enough training data. To address this limitation, in this work we propose a novel method in which the large-scale pre-trained language model GPT-2 is employed to generate synthetic training data for OSD. In particular, we propose to train the GPT-2 model in a dual-training setting using the REINFORCE algorithm to generate in-domain, natural and diverse training samples. Extensive experiments on the benchmark dataset for OSD reveal the effectiveness of the proposed method.