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.
After several introductory lectures by Alex Fraser 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.
The language of the course is English.
Schein: if you are interested in a Schein for this SS 2010 course, please let us know by email. We expect this would be a presentation of a research paper taken from the literature, preferably in English (however, if several students are interested we might reserve one or two days for presentations in German).
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
We meet on Wednesdays at 14:00 in the IMS phonetics lab (top floor, last room on the right. Institut fuer Maschinelle Sprachverarbeitung, Azenbergstrasse 12).
The five initial meetings:
April 28th, 14:00, 3.11 (IMS Phonetik Labor) Alex Fraser: Introduction to statistical machine translation - Part 1. Introduction, basics of statistical machine translation (SMT), evaluation of MT
May 5th, 14:00, 3.11 Alex Fraser: Introduction to statistical machine translation - Part 2. Bitext alignment (extracting lexical knowledge from parallel corpora)
May 12th, 14:00, 3.11 Alex Fraser: Introduction to statistical machine translation - Part 3. Decoding (automatically translating a text given an already learned model)
May 19th, 14:00, 3.11 Alex Fraser: Introduction to statistical machine translation - Part 4. Log-linear models for SMT
May 26th, 14:00, 3.11 Alex Fraser: Introduction to statistical machine translation - Part 5. Advanced topics in SMT. Discriminative bitext alignment, morphological processing, syntax