97 citations · 350 across the 43 of their papers we have counts for
6 papers · 1 filter
Validity problems in clinical machine learning by indirect data labeling using consensus definitions
Michael Hagmann, Shigehiko Schamoni, Stefan Riezler
We demonstrate a validity problem of machine learning in the vital application area of disease diagnosis in medicine. It arises when target labels in training data are determined b…
Text-to-OverpassQL: A Natural Language Interface for Complex Geodata Querying of OpenStreetMap
Michael Staniek, Raphael Schumann, Maike Züfle +1
We present Text-to-OverpassQL, a task designed to facilitate a natural language interface for querying geodata from OpenStreetMap (OSM). The Overpass Query Language (OverpassQL) al…
Improving End-to-End Speech Translation by Imitation-Based Knowledge Distillation with Synthetic Transcripts
Rebekka Hubert, Artem Sokolov, Stefan Riezler
End-to-end automatic speech translation (AST) relies on data that combines audio inputs with text translation outputs. Previous work used existing large parallel corpora of transcr…
Enhancing Supervised Learning with Contrastive Markings in Neural Machine Translation Training
Nathaniel Berger, Miriam Exel, Matthias Huck +1
Supervised learning in Neural Machine Translation (NMT) typically follows a teacher forcing paradigm where reference tokens constitute the conditioning context in the model's predi…
VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View
Raphael Schumann, Wanrong Zhu, Weixi Feng +3
Incremental decision making in real-world environments is one of the most challenging tasks in embodied artificial intelligence. One particularly demanding scenario is Vision and L…
Towards Inferential Reproducibility of Machine Learning Research
Michael Hagmann, Philipp Meier, Stefan Riezler
Reliability of machine learning evaluation -- the consistency of observed evaluation scores across replicated model training runs -- is affected by several sources of nondeterminis…