Chair of Linguistic Informatics
Prof. Dr. Stefan Riezler
Institut für Computerlinguistik,
Im Neuenheimer Feld 325
69120 Heidelberg, Germany
|Office hours||Wednesdays, 11:15–12:45 (Students: Please send an email in advance!)|
|Phone||+49 6221 54-3097|
- Stochastic modeling of natural language, including statistical parsing, clustering, summarization, machine translation, question answering, information retrieval.
- Statistical machine learning methods, especially unsupervised, semi-supervised and discriminative learning techniques.
- New papers:
- To appear: Stefan Riezler. On the Problem of Theoretical Terms in Empirical Computational Linguistics. In Computational Linguistics 40(1), 2014 (draft paper / CL journal link)
- We participated in the IWSLT evaluation campaign for spoken language translation for German-to-English, Russian-to-English and English-to-Russian. Here is the system description.
- Big Learning workshop at NIPS: Artem Sokolov, Stefan Riezler. Task-driven Greedy Learning of Feature Hashing Functions. In Proceedings of the Workshop on Big Learning at the Conference on Neural Information Processing Systems (NIPS 2013), Lake Tahoe, Nevada. (.pdf)
- Here is the full publication list.
- I am program co-chair of the 14th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2014), which will happen in Gothenburg, Sweden, from April 26 to 30, 2014. Please visit the EACL 2014 webpage.
- New data releases:
- BoostCLIR: A Japanese-English corpus of patent abstracts for patent prior art search, consisting of 100K queries and relevance judgements for 1.4M documents. For more information and download, please see the BoostCLIR page.
- PatTR: A parallel patent corpus of 23 million German-English, 18 million French-English, and 5 million German-French sentences for statistical machine translation. For more information and download, please see the PatTR page.