Title: spMMMP at GermEval 2018 shared task : classification of offensive content in tweets using convolutional neural networks and gated recurrent units
Authors : von Grünigen, Dirk
Grubenmann, Ralf
Benites de Azevedo e Souza, Fernando
von Däniken, Pius
Cieliebak, Mark
Published in : Proceedings of the GermEval 2018 Workshop : 14th Conference on Natural Language Processing - KONVENS 2018
Pages : 130
Pages to: 137
Conference details: 14th Conference on Natural Language Processing (KONVENS 2018), Vienna, Austria, 19-21 September 2018
Publisher / Ed. Institution : ÖAW Austrian Academy of Sciences
Issue Date: 21-Sep-2018
License (according to publishing contract) : Licence according to publishing contract
Type of review: Editorial review
Language : English
Subjects : Hate Speech; Shared task
Subject (DDC) : 004: Computer science
Abstract: 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.
Departement: School of Engineering
Organisational Unit: Institute of Applied Information Technology (InIT)
Publication type: Conference Paper
URI: https://www.oeaw.ac.at/fileadmin/subsites/academiaecorpora/PDF/GermEval2018_Proceedings.pdf
https://digitalcollection.zhaw.ch/handle/11475/11415
Appears in Collections:Publikationen School of Engineering

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.