GermEval2024 Shared Task: GerMS-Detect -- Sexism Detection and Annotator Disagreement Prediction in German Online News Fora
2nd CALL FOR PARTICIPATION
We would like to invite you to the GermEval Shared Task GerMS-Detect on
Sexism Detection in German Online News Fora collocated with Konvens 2024 <
https://ofai.github.io/GermEval2024-GerMS/>.
Competition Website:
https://ofai.github.io/GermEval2024-GerMS/
Important Dates:
* Development phase: May 1 - June 5, 2024 (ongoing)
* Competition phase: June 7 - June 25, 2024
* Paper submission due: July 1, 2024
* Camera ready due: July 20, 2024
* Shared Task @KONVENS: 10 September, 2024
Task description
This shared task is not just about the detection of sexism/misogyny in
comments posted in (mostly) German language to the comment section of an Austrian online newspaper: many of the texts to be classified contain
ambiguous language, very subtle ways to express misogyny or sexism or
lack important context. For these reasons, there can be quite some
disagreement between annotators on the appropriate label. In many cases,
there is no single correct label. For this reason the shared task is not
just about correctly predicting a single label chosen from all the
labels assigned by human annotators, but about models which can predict
the level of disagreement, the range of labels assigned by annotators or
the distribution of labels to expect for a specific group of annotators.
For details see the Competition Website:
https://ofai.github.io/GermEval2024-GerMS/
Organizers
The task is organized by the Austrian Research Institute for Artificial Intelligence (OFAI):
https://www.ofai.at/
Organizing team:
Brigitte Krenn (brigitte.krenn (AT) ofai.at)
Johann Petrak (johann.petrak (AT) ofai.at)
Stephanie Gross (stephanie.gross (AT) ofai.at)
--
Dr.-Ing. Tristan Miller, Associate Research Scientist
Austrian Research Institute for Artificial Intelligence (OFAI)
Freyung 6/6, 1010 Vienna, Austria | Tel: +43 1 5336112 12
https://logological.org/ |
https://punderstanding.ofai.at/
--- SoupGate-Win32 v1.05
* Origin: fsxNet Usenet Gateway (21:1/5)