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

In the winter semester 2014/15 the Lehrstuhl 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 Computer Science Department.

Prerequisites for participation in the seminar

Seminar format and important dates

The seminar will take place in block mode, i.e. all presentations will be held in a short period after the end of the lecture period.
The presentation block is scheduled for

Monday and Tuesday, March 2 and 3, 2015, 9-17h,

incl. lunch breaks. The order of the presentations will be as shown here. Nevertheless, to be able to accomodate changes in the presentation order if necessary on short notice, we ask all participants to be prepared by the first day of the presentation block and have their slides ready.

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 kick-off meeting (i.e. by Aug. 29, 2014) results in the grade 5.0/not appeared.

Topics, relevant references and participants

The specific topics of the seminar can be found below and are introduced and distributed during the preparatory meeting.

List of seminar topics:

Topics w/o prior knowledge:
  1. Machine Translation Evaluation (NN; Supervisor: Markus Freitag)
    References:
    • K. Papineni, S. Roukus, T. Ward and W. Zhu: "BLEU: a Method for Automatic Evaluation of Machine Translation," in Proc. ACL, pp. 311-318, Philadelphia, PA, July 2002.
    • M. Snover, B. Dorr, R. Schwartz, L. Micciulla, and J. Makhoul: "A Study of Translation Edit Rate with Targeted Human Annotation," in Proc. AMTA, pp. 223-231. August 2006.
    • A. Lavie, and A. Agarwal: "METEOR: An Automatic Metric for MT Evaluation with High Levels of Correlation with Human Judgments," in Proc. WMT, pp. 228-231, Prague, Czech Republic, June 2007.

  2. IBM Translation Models (NN; Supervisor: Andy Guta)
    References:
    • Chapter 4 of P. Koehn: "Statistical Machine Translation," textbook, Cambridge University Press, January 2010.
    • F. Och, and H. Ney: "Improved statistical alignment models," in Proc. ACL, pp. 440-447, Hong Kong, 2000.

  3. Decoding for Phrase-Based Statistical Machine Translation (NN; Supervisor: Joern Wübker)
    References:
    • Chapter 6 of P. Koehn: "Statistical Machine Translation," textbook, Cambridge University Press, January 2010.
    • P. Koehn: "Pharaoh: a Beam Search Decoder for Phrase-Based Statistical Machine Translation Models," in Proc. AMTA, Washington, DC, September 2004.

  4. Hierarchical Phrase-based Machine Translation (Timmermanns; Supervisor: Stephan Peitz)
    References:

  5. N-gram-based Machine Translation (NN; Supervisor: Andy Guta)
    References:
    • J, Mariño, R. Banchs, J. Crego, A. Gispert, P. Lambert, J. Fonollosa, and M. Costa-jussà: "N-gram-based Machine Translation," in Computational Linguistics, Vol. 32(4), pp. 527-549, December 2006.

  6. Lightly-Supervised Training for Statistical Machine Translation (Hamadache; Supervisor: Malte Nuhn)
    References:

  7. Large Scale Parallel Document Mining for Machine Translation (Frohn; Supervisor: Malte Nuhn)
    References:

  8. System Combination for Machine Translation (Wallraff; Supervisor: Markus Freitag)
    References:

  9. Deciphering Foreign Language (Richter; Supervisor: Malte Nuhn)
    References:

Topics with prior knowledge:
  1. Operation Sequence Model (Graça; Supervisor: Andy Guta)
    References:

  2. Discriminative Training for MT (Vaitl; Supervisor: Joern Wübker)
    References:

  3. Word Alignment with Neural Network (Soliman; Supervisor: Jan-Thorsten Peter)
    References:

  4. Neural Network in Decoding (Rossenbach; Supervisor: Jan-Thorsten Peter)
    References:

  5. Recurrent Neural Networks for Translation Modelling (NN; Supervisor: Joern Wübker)
    References:
    • S. Liu, N. Yang, M. Li, and M. Zhou: "A Recursive Recurrent Neural Network for Statistical Machine Translation," in Proc. ACL, pp. 1491-1500, Baltimore, Maryland, USA, June 2014
    • N. Kalchbrenner, P. Blunsom: "Recurrent Continuous Translation Models," in Proc. EMNLP, pp. 1700-1709, Seattle, WA, Oct. 2013.

  6. Syntax-based Machine Translation - String To Tree (Bretschner; Supervisor: Stephan Peitz)
    References:

  7. Syntax-based Machine Translation - Tree To String (Schupp; Supervisor: Stephan Peitz)
    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 have to be prepared in LaTeX format using the provided templates 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:

Dr. Ralf Schlüter
RWTH Aachen
Lehrstuhl Informatik 6
Ahornstr. 55
52056 Aachen Raum 6125b
Telefon: 0241 / 80-21612
E-Mail: schlueter@cs.rwth-aachen.de