Michael A. Hedderich


My current research focuses on machine learning for low-resource settings, especially but not limited to the field of natural language processing. Connected to this, I'm working on distant supervision techniques and learning with noisy or unreliable labels. I'm also interested in applications of machine learning in other fields such as human-computer-interaction as well as in better interpretability of neural networks and their training processes.

Current affiliations:

In the past, I had the pleasure to work with


Recent News:
  • I'm a co-organizer of the Business Meets Technology conference at Hochschule Ansbach, Germany.
  • We presented our work on machine learning for low-resource African languages.
  • We presented our latest work on learning with noisy labels at EMNLP 2019.
  • We gave a talk about our work on intelligibility and language modelling at RAILS 2019.
  • I gave a talk on machine learning in low-resource scenarios at TaCoS 2019.
Past News:
  • I presented our work on multi-sense word embeddings with a talk at IWCS 2019.
  • A former student presented our work on learning with noisy data from self-training at the NAACL SRW 2019.
  • I gave a guest lecture at the Ambient Intelligence group at Aalto University. The slides can be found here.
  • At the ACL 2018 workshop DeepLo, I gave a talk about our work on learning with noisily labeled, automatically annotated data.