Publications
Chosen filters:
Chosen filters:
Whisper-SLU: Extending a pretrained speech-to-text transformer for low resource spoken language understanding KU Leuven
In recent years, transformers have become a fundamental part of machine learning research and have demonstrated impressive results in various fields. However, they require significant resources for training. This paper proposes extending the Whisper transformer-based model with dedicated modules for low resource spoken language understanding tasks, including named entity recognition and intent recognition. The authors borrow techniques from ...
Causal Factor Disentanglement for Few-Shot Domain Adaptation in Video Prediction KU Leuven
An important challenge in machine learning is performing with accuracy when few training samples are available from the target distribution. If a large number of training samples from a related distribution are available, transfer learning can be used to improve the performance. This paper investigates how to do transfer learning more effectively if the source and target distributions are related through a Sparse Mechanism Shift for the ...
Preventing profiling for ethical fake news detection KU Leuven
A news article's online audience provides useful insights about the article's identity. However, fake news classifiers using such information risk relying on profiling. In response to the rising demand for ethical AI, we present a profiling-avoiding algorithm that leverages Twitter users during model optimisation while excluding them when an article's veracity is evaluated. For this, we take inspiration from the social sciences and introduce two ...