Personal
Welcome to the homepage of Martin Ratajczak.
Currently I work within the Human Language Technology and Pattern Recognition Group
at the Chair of Computer Science 6 of the RWTH Aachen University.
The main research topics of the chair are
- Pattern Recognition
- Automatic Speech Recognition
- Statistical Machine Translation
- Image Processing
My personal research topics and interests are
- Conditional Random Fields (CRFs)
- Maximum Entropy Markov Models (MEMMs)
- Application of MEMMs and CRFs to sequence labeling tasks: Mainly statistical machine translation, tagging and sign language translation
- Discriminative Word Lexicon Models (DWLs)
- Feature Selection
- Speed up training of log-linear models
- Text classification
You can find me in room 6127 of our department, call me at +49 (241) 80-21618 or write an e-mail to ratajczak [-at-] i6.informatik.rwth-aachen.de.
Publications
Talks and Presentations
Selected talks and presentations (other than those associated with conference publications):
- Maximum Entropy Feature Selection for DWL Model. Talk at Quaero CRF Workshop. Paris, France, August 2010.
Teaching
Projects
- Quaero, funded by OSEO, French State agency for innovation
- GALE (Global Autonomous Language Exploitation), funded by the Defense Advanced Research Projects Agency (DARPA)
List of projects
of the chair.
Evaluations
Participation in machine translation evaluation campaigns:
- Quaero Machine Translation Evaluation 2011
- French-to-German PBT systems
- German-to-French PBT systems
- German-to-French PBT systems for translation of speech
- French-to-German PBT systems for translation of speech
- Quaero Machine Translation Evaluation 2010
- French-to-German PBT systems
- German-to-French PBT systems
- German-to-French PBT systems for translation of speech
- French-to-German PBT systems for translation of speech
- Quaero Machine Translation Evaluation 2009
- French-to-German PBT systems
- German-to-French PBT systems
- German-to-French PBT systems for translation of speech
- French-to-German PBT systems for translation of speech