Seminar "Selected Topics in Human Language Technology and Pattern Recognition"

In the summer term 2012 the Lehrstuhl für Informatik 6 will host a seminar entitled "Selected Topics in Human Language Technology and Pattern Recognition".

Registration for the seminar

Registration for the seminar is only possible online via the registration page provided by the department.

Prerequisites for participation in the seminar

Seminar format and important dates

The seminar generally takes place in block mode around the end of the lecture period. Specific dates will be arranged.

Note: failure to meet deadlines, absence without permission from compulsory sessions (presentations and preliminary meeting as announced by email to each participating student), or dropping out of the seminar after more than 3 weeks after the preliminary meeting/topic distribution results in the grade 5.0/not appeared.

Topics, relevant references and participants

Specific topics will be introduced at a preparatory meeting in the seminar room at the Lehrstuhl für Informatik 6.
In general, selected topics from the following general areas of Human Language Technology and Pattern Recognition will be offered: Some possible topics, supervisors, and basic references:
  1. The IBM Translation Models (Kohnen; Supervisor: Christoph Schmidt)
    References:
  2. Decoding for Phrase-Based Statistical Machine Translation (Rietig; Supervisor: Stephan Peitz)
    References:
  3. Machine Translation Evaluation (Kochanov; Supervisor: Markus Freitag)
    References:
  4. Phrase Table Smoothing for Statistical Machine Translation (NN; Supervisor: Saab Mansour)
    References:
  5. Domain Adaptation for Statistical Machine Translation (Erduran; Supervisor: Saab Mansour)
    References:
  6. Unsupervised Training for Statistical Machine Translation (Mroz; Supervisor: Malte Nuhn)
    References:
  7. System Combination for Machine Translation (NN; Supervisor: Markus Freitag)
    References:
  8. Morphological and Syntactic Processing for Statistical Machine Translation (Schimitzek; Supervisor: Jan-Thorsten Peter)
    References:
  9. Discriminative Alignment for Machine Translation (NN; Supervisor: Christoph Schmidt)
    References:
  10. Discriminative Training for Machine Translation (Muehr; Supervisors: Jörn Wübker, Matthias Huck)
    References:
  11. Reordering for Phrase-based Statistical Machine Translation (NN; Supervisor: Matthias Huck)
    References:
  12. Hierarchical Phrase-based Machine Translation (NN; Supervisor: Matthias Huck)
    References:
  13. Syntax-based Statistical Machine Translation (NN; Supervisor: Stephan Peitz)
    References:
  14. Treelet Translation (NN; Supervisor: Jörn Wübker)
    References:
  15. Semantics for Statistical Machine Translation (Pasdziernik; Supervisor: Minwei Feng)
    References:

Guidelines for the article and presentation

The roughly 20-page article together with the slides (between 20 & 30) for the presentation should be prepared in LaTeX format. Presentations will consist of 45 minutes presentation time & 15 minutes discussion time. Document templates for both the article and the presentation slides are provided below along with links to LaTeX documentation available online. The article and the slides should be prepared in LaTeX format and submitted electronically in pdf format. Other formats will not be accepted.

             General:
             Specific:

Contact

Inquiries should be directed to the respective supervisors or to:

Matthias Huck
RWTH Aachen
Lehrstuhl für Informatik 6
Ahornstr. 55
52056 Aachen

Room 6126 (1. Etage E2)
Telephone: 0241 / 80 21 617
E-Mail: huck [-at-] cs.rwth-aachen.de