Ruprecht-Karls-Universität Heidelberg

Statistical Natural Language Processing Group

Welcome to the Statistical Natural Language Processing Group at the Institute for Computational Linguistics at Heidelberg University. Our research addresses various aspects of the problem of the confusion of languages, by means of interactive statistical learning techniques, for example, learning from human reinforcement/bandit feedback.
We organize the weekly Statistical NLP Colloquium.


  • Launching our blog

      We entered the blogosphere with the StatNLP HD Blog. Our posts will focus on pitfalls in methodologies, recent advances and important problems in our field of research.
  • New DFG-funded project on Interactive Lecture Translation

      A new research project on auto-adaptive learning from weak feedback for interactive machine lecture translation will soon start. The project attempts to learn machine translation from bandit feedback in form of judgements on the quality of a predicted translation without requiring a post-edit or a gold-standard translation. The application scenario is the translation of university lectures, a focus which is shared with parallel projects at RWTH Aachen, KIT Karlsruhe, and the University of the Saarland, Saarbrücken.


Former Members

zum Seitenanfang