Chair of Linguistic Informatics
Prof. Dr. Stefan Riezler
Institut für Computerlinguistik,
Im Neuenheimer Feld 325
69120 Heidelberg, Germany
||+49 6221 54-3245 (Secretary)
Stefan Riezler joined Heidelberg University as full professor in 2010, after spending a decade in the worldâ€™s most renowned industry research labs (Xerox PARC
, Google Research
). He received his PhD in Computational Linguistics from the University of TĂĽbingen
in 1998, and then conducted post-doctoral work at Brown University
in 1999. Prof. Riezler's research focus is on machine learning for natural language processing problems, especially for the application areas of cross-lingual information retrieval and statistical machine translation. He is engaged in the area of Computational Linguistics, e.g., as editorial board member of the main journals Computational Linguistics
and Transactions of the Association for Computational Linguistics
, and conducts interdisciplinary research as member of the Interdisciplinary Center for Scientific Computing
and as Marsilius Fellow
at Heidelberg University.
New work on Bandit Structured Prediction accepted at EMNLP 2017 and WMT 2017:
Counterfactual Learning from Bandit Feedback under Deterministic Logging: A Case Study in Statistical Machine Translation. Carolin Lawrence, Artem Sokolov, Stefan Riezler. EMNLP 2017
A Shared Task on Bandit Learning for Machine Translation. Artem Sokolov, Julia Kreutzer, Kellen Sunderland, Pavel Danchenko, Witold Szymaniak, Hagen Fürstenau, Stefan Riezler. WMT 2017
Paper accepted at ACL 2017: Bandit Structured Prediction for Neural Sequence-to-Sequence Learning. Julia Kreutzer, Artem Sokolov, Stefan Riezler.
Shared Task on Bandit Learning for Machine Translation organized by Statistical NLP group and Amazon Development Center, Berlin
Amazon and University of Heidelberg organize a Shared Task on Bandit Learning for Machine Translation with the goal to encourage researchers to investigate algorithms for learning from weak user feedback instead of from human references or post-edits that require skilled translators. We are interested in finding systems that learn efficiently and effectively from this type of feedback, i.e. they learn fast and achieve high translation quality. Developing such algorithms is interesting for interactive machine learning and for human feedback in NLP in general. See the WMT17 page for more information.
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.