Germeval Task 2, 2019 — Shared Task on the Identification of Offensive Language
Overview
Introduction
Offensive Language is commonly defined as hurtful, derogatory or obscene comments made by one person to another person. Such type of language can be more increasingly found on the web. As a consequence many operators of social media websites no longer manage to manually monitor user posts. Therefore, there is a pressing demand for methods to automatically identify suspicious posts.
This shared task is to initiate and foster research on the identification of offensive content in German language microposts. Offensive comments are to be detected from a set of German tweets. We focus on Twitter since they can be regarded as a prototypical type of micropost.
The workshop discussing2019’s edition of this shared task was held in conjunction with the Conference on Natural Language Processing KONVENS
The focus of this evaluation campaign lies on the linguistic analysis of offensive content that can be found on the web. We therefore only provide textual data and consider this task as a text classification problem. We are aware of the fact that such content can also be conveyed via other modes, such as images of videos. However, for the sake of keeping the complexity of the task at an acceptable level, we refrained from including them in our task.
The organizers exclusively have a linguistic interest in this subject matter. In no way is it their intention to promote a specific political or cultural view. Therefore, offensive language will be marked as such irrespective of its origin.
Warning
The examples listed on this website and also the actual data we provide in this shared task include very explicit language. These contents do not reflect the views of the organizers. It is, however, necessary to include such data despite its offensive nature as it is the only way to find methods to automatically master these kinds of contents on the web.
Workshop
The GermEval workshop 2019 is part of Konvens 2019 in Erlangen. The pre-conference workshop takes place on Tuesday (October 08, 2019).
Workshop Program
11:00 | Registration and Welcoming (KH 0.019) |
11:30 | Presentations on GermEval Task 1 (KH 0.023) |
Steffen Remus, Rami Aly and Chris Biemann: GermEval 2019 Task 1: Hierarchical Classification of Blurbs | |
Venkatesh Umaashankar and Girish Shanmugam S: Multi-Label Multi-Class Hierarchical Classification using Convolutional Seq2Seq | |
Fernando Benites: TwistBytes – Hierarchical Classification at GermEval 2019: walking the fine line (of recall and precision) | |
Malte Ostendorff, Peter Bourgonje, Maria Berger, Julián Moreno-Schneider, Georg Rehm and Bela Gipp: Enriching BERT with Knowledge Graph Embeddings for Document Classification | |
13:00 | Lunch break |
14:30 | Presentations on GermEval Task 2 (KH 0.023) |
Julia Maria Struß, Melanie Siegel, Josef Ruppenhofer, Michael Wiegand and Manfred Klenner: Overview of GermEval Task 2, 2019 — Shared Task on the Identification of Offensive Language | |
Julian Risch, Anke Stoll, Marc Ziegele and Ralf Krestel: hpiDEDIS at GermEval 2019: Offensive Language Identification using a German BERT model | |
Johannes Schäfer, Tom De Smedt and Sylvia Jaki:HAU at the GermEval 2019 Shared Task on the Identification of Offensive Language in Microposts: System Description of Word List, Statistical and Hybrid Approaches | |
16:00 | Poster Session w/ coffee (KH 0.024) : |
GermEval Task 1 posters: Franz Bellmann, Lea Bunzel, Christoph Demus, Lisa Fellendorf, Olivia Gräupner, Qiuyi Hu, Tamara Lange, Alica Stuhr, Jian Xi, Dirk Labudde and Michael Spranger: Multi-Label Classification of Blurbs with SVM Classifier Chains | |
David S. Batista and Matti Lyra: COMTRAVO-DS team at GermEval 2019 Task 1 on Hierarchical Classification of Blurbs | |
Erdan Genc, Louay Abdelgawad, Viorel Morari and Peter Kluegl: Convolutional Neural Networks for Classification of German Blurbs | |
Melanie Andresen, Melitta Gillmann, Jowita Grala, Sarah Jablotschkin, Lea Röseler, Eleonore Schmitt, Lena Schnee, Katharina Straka, Michael Vauth, Sandra Kübler and Heike Zinsmeister: The HUIU Contribution to the GermEval 2019 Shared Task 1 | |
Raghavan A. K. and Venkatesh Umaashankar: Label Frequency Transformation for Multi-Label Multi-Class Text Classification | |
Kristian Rother and Achim Rettberg: Logistic Regression and Naive Bayes for Hierarchical Multi-label Classification at GermEval 2019 – Task 1 | |
GermEval Task 2 posters: | |
Michele Corazza, Stefano Menini, Elena Cabrio, Sara Tonelli and Serena Villata: InriaFBK Drawing Attention to Offensive Language at Germeval2019InriaFBK Drawing Attention to Offensive Language at Germeval2019 Kristian Rother and Achim Rettberg: German Hatespeech classification with Naive Bayes and Logistic Regression – hshl at GermEval 2019 – Task 2 | |
Theresa Krumbiegel: FKIE – Offensive Language Detection on Twitter at GermEval 2019 | |
Inna Vogel and Roey Regev: FraunhoferSIT at GermEval 2019: Can Machines Distinguish Between Offensive Language and Hate Speech? Towards a Fine-Grained Classification Florian Schmid, Justine Thielemann, Anna Mantwill, Jian Xi, Dirk Labudde and Michael Spranger: FoSIL – Offensive language classification of German tweets combining SVMs and deep learning techniques | |
Isabell Börner, Midhad Blazevic, Maximilian Komander and Margot Mieskes: 2019 GermEval Shared Task on Offensive Tweet Detection h da submission | |
Melanie Andresen, Melitta Gillmann, Jowita Grala, Sarah Jablotschkin, Lea Röseler, Eleonore Schmitt, Lena Schnee, Katharina Straka, Michael Vauth, Sandra Kübler and Heike Zinsmeister: The HUIU Contribution for the GermEval Shared Task 2 | |
17:30 | Presentation on GermEval Task 2 (KH 0.023) |
Andrei Paraschiv and Dumitru-Clementin Cercel: | |
UPB at GermEval-2019 Task 2: BERT-Based Offensive Language Classification of German Tweets | |
18:00 | Closing Remarks & Discussion (KH 0.023) |