The success of statistical machine translation systems such as Moses, Language Weaver, Google Translate and many others, has shown that it is possible to build high performance machine translation systems with a small amount of effort using statistical learning techniques.
It is already clear that statistical parsing will be a key technology for future approaches to statistical machine translation.
After several introductory lectures by Alex Fraser and Helmut Schmid we will alternate informal presentations of research papers by members of the group. Our initial goal is to reach the point where we are able to read about and discuss new ideas in statistical machine translation research involving the integration of linguistic representations ranging from deep to shallow.
Alexander Fraser and Helmut Schmid
EMAIL ADDRESSES: SubstituteLastName@ims.uni-stuttgart.de
Institute for Natural Language Processing (IMS/IfNLP)
SFB 732 - Incremental Specification in Context
Meeting 1: Alex Fraser: Introduction to statistical machine translation - Part 1. Introduction, basics of statistical machine translation (SMT), evaluation of MT
Meeting 2: Alex Fraser: Introduction to statistical machine translation - Part 2. Bitext alignment (extracting lexical knowledge from parallel corpora)
Meeting 3: Alex Fraser: Introduction to statistical machine translation - Part 3. Phrase-based Modeling and Decoding
Meeting 4: Alex Fraser: Introduction to statistical machine translation - Part 4. Log-linear models and minimum error rate training
Meeting 5: Alex Fraser: Introduction to statistical machine translation - Part 5. Advanced topics in SMT.
Meeting 6: Helmut Schmid: Introduction to HMM tagging
Meeting 7: Helmut Schmid: Introduction to CFG parsing algorithms
Meeting 8: Helmut Schmid: PCFG parsing algorithms
Meeting 9: Helmut Schmid: PCFG parsing algorithms continued