RGCL at GermEval 2019: Offensive Language Detection with Deep Learning.
Alistair Plum, Tharindu Ranasinghe, Constantin Orǎsan, Ruslan Mitkov · Open Repository and Bibliography (University of Luxembourg) · 2019
This paper describes the system submitted by the RGCL team to GermEval 2019 Shared Task 2: Identification of Offensive Language. We experimented with five different neural network architectures in order to classify Tweets in terms of offensive language. By means of comparative evaluation, we select the best performing for each of the three subtasks. Overall, we demonstrate that using only minimal preprocessing we are able to obtain competitive results.