1 code implementation • 28 Mar 2024 • Janis Goldzycher, Paul Röttger, Gerold Schneider
Our experiments show that the resulting dataset is challenging even for state-of-the-art hate speech detection models, and that training on GAHD clearly improves model robustness.
1 code implementation • 6 Jun 2023 • Janis Goldzycher
The widespread popularity of social media has led to an increase in hateful, abusive, and sexist language, motivating methods for the automatic detection of such phenomena.
1 code implementation • 6 Jun 2023 • Janis Goldzycher, Moritz Preisig, Chantal Amrhein, Gerold Schneider
In this paper, we test whether natural language inference (NLI) models which perform well in zero- and few-shot settings can benefit hate speech detection performance in scenarios where only a limited amount of labeled data is available in the target language.
1 code implementation • TRAC (COLING) 2022 • Janis Goldzycher, Gerold Schneider
We find that the zero-shot baseline used for the initial error analysis already outperforms commercial systems and fine-tuned BERT-based hate speech detection models on HateCheck.
no code implementations • RANLP 2019 • Tannon Kew, Anastassia Shaitarova, Isabel Meraner, Janis Goldzycher, Simon Clematide, Martin Volk
Geotagging historic and cultural texts provides valuable access to heritage data, enabling location-based searching and new geographically related discoveries.