Image: Network

GermEval

GermEval

GermEval is a series of shared task evaluation campaigns that focus on Natural Language Processing for the German language. So far, there have been four iterations of GermEval, each with a different type of task (see table below). GermEval shared tasks have been run informally by self-organized groups of interested researchers. However, the last shared tasks were endorsed by special interest groups within the German Society for Computational Linguistics (GSCL). All iterations of GermEval shared tasks held their concluding workshop in conjunction with either the GSCL or the KONVENS bi-annual conferences, depending on which of them took place.

Year

Topic

Link

Organizers

2014

Named Entity Recognition

sites.google.com/site/germeval2014ner/

Darmstadt / Stuttgart

2015

Lex(ical)Sub(stitution)

sites.google.com/site/germeval2015/

Hamburg / Darmstadt

2017

Aspect-based Sentiment in Social Media Customer Feedback

sites.google.com/view/germeval2017-absa/home

Hamburg / Duisburg-Essen

2018

Identification of Offensive Language

fz.h-da.de/iggsa/germeval

Darmstadt, Saarbrücken, Heidelberg

2019

Hierarchical Classification of Blurbs

competitions.codalab.org/competitions/21226

Hamburg Konvens@ Erlangen

2019

Identification of Offensive Language

fz.h-da.de/iggsa/germeval

Darmstadt, Zürich, Heidelberg, Mannheim, Potsdam

GermEval Task 2018 — Shared Task on the Identification of Offensive Language

The proceedings of GermEval Task 2018 can be found here

The results of the evaluation, that is, the ranking of all system runs that were submitted to the shared task, are publicly available via the following GIT-repository:
https://github.com/uds-lsv/GermEval-2018-Data

A summary of the survey is available at: https://github.com/uds-lsv/GermEval-2018-Data

Workshop Program

The workshop was held on Friday, September 21, in Vienna. The workshop program can be found at: https://www.oeaw.ac.at/fileadmin/subsites/academiaecorpora/PDF/WorkshopAgenda.pdf.