RGCL at GermEval 2019: offensive language detection with deep learning
Abstract
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.Citation
Plum, A., Ranasinghe, T., Orasan, C. and Mitkov, R. (2019) RGCL at GermEval 2019: offensive language detection with deep learning. Preliminary proceedings of the 15th Conference on Natural Language Processing (KONVENS 2019). Erlangen, Germany, pp. 421-426.Additional Links
https://2019.konvens.org/proceedingsType
Conference contributionLanguage
en
Except where otherwise noted, this item's license is described as https://creativecommons.org/licenses/by-nc-sa/4.0/