AIT_FHSTP at GermEval 2021: Automatic Fact Claiming Detection with Multilingual Transformer Models

no code implementations • GermEval 2021 • Jaqueline Böck, Daria Liakhovets, Mina Schütz, Armin Kirchknopf, Djordje Slijepčević, Matthias Zeppelzauer, Alexander Schindler

Our best model is GottBERT (i. e., a BERT transformer pre-trained on German texts) fine-tuned on the GermEval 2021 data.

F1 Score Transformer

Explaining YOLO: Leveraging Grad-CAM to Explain Object Detections

no code implementations • 22 Nov 2022 • Armin Kirchknopf, Djordje Slijepcevic, Ilkay Wunderlich, Michael Breiter, Johannes Traxler, Matthias Zeppelzauer

We investigate the problem of explainability for visual object detectors.

Object

Automatic Sexism Detection with Multilingual Transformer Models

no code implementations • 9 Jun 2021 • Mina Schütz, Jaqueline Boeck, Daria Liakhovets, Djordje Slijepčević, Armin Kirchknopf, Manuel Hecht, Johannes Bogensperger, Sven Schlarb, Alexander Schindler, Matthias Zeppelzauer

For both tasks our best model is XLM-R with unsupervised pre-training on the EXIST data and additional datasets and fine-tuning on the provided dataset.

Binary Classification F1 Score +4

Multimodal Detection of Information Disorder from Social Media

no code implementations • 31 May 2021 • Armin Kirchknopf, Djordje Slijepcevic, Matthias Zeppelzauer

Social media is accompanied by an increasing proportion of content that provides fake information or misleading content, known as information disorder.

Fake News Detection