spMMMP at GermEval 2018 Shared Task: Classification of Offensive Content in Tweets using Convolutional Neural Networks and Gated Recurrent Units

In this paper, we propose two different systems for classifying offensive language in micro-blog messages from Twitter (”tweet”). The first system uses an ensemble of convolutional neural networks (CNN), whose outputs are then fed to a meta-classifier for the final prediction. The second system uses a combination of a CNN and a gated recurrent unit (GRU) together with a transfer-learning approach based on pretraining with a large, automatically translated dataset