Seminar in Main Studies

Deutsch

In the summer term 2007 the Lehrstuhl für Informatik 6 will host a seminar entitled:

Seminar "Training Methods in Pattern Recognition"

Registration for the seminar:

Registration for the seminar is only possible online via the registration page provided by the institute. A link can be found on the Computer Science Department's homepage.

Prerequisites for participation in the seminar:

• Vordiplom or Bachelor degree
  
• Attendance of the lectures Pattern Recognition and Neural Networks, Speech Recognition or Statistical Methods in Natural Language Processing, or evidence of equivalent knowledge.
  

Seminar format and important dates:

The seminar will take place at the following dates:

• Proposals: initial proposals will be accepted up until the start of the term (April 2nd, 2007) at the Lehrstuhl für Informatik 6 office or by the relevant supervisor. At this time participants must arrange an appointment with the relevant supervisor. Revised proposals will be accepted up until two weeks after the start of the term.
• Article: must be submitted at least 1 month prior to the trial presentation date to either the Lehrstuhl für Informatik 6 office or the relevant supervisor.
  
• Presentation slides: must be submitted at least 1 week prior to the trial presentation date to either the Lehrstuhl für Informatik 6 office or the relevant supervisor.
• Trial presentations: at least 2 weeks prior to the actual presentation date; refer to the section on topics.
• Seminar presentations: the exact dates and plan for the presentation block (expected to be around the end of July 2007) will be arranged and announced for the individual topics.
• Final (possibly corrected) articles and presentation slides: must be submitted at the latest 2 weeks after the presentation date to either the Lehrstuhl für Informatik 6 office or the relevant supervisor.
• Compulsory attendance: in order to receive a certificate participants must attend all presentation sessions.

Note: Deadlines are binding. Failure to meet deadlines can lead to exclusion from the seminar.

Topics, Relevant References and Participants:

1. Introduction to Kernel Methods (Schmitz; Supervisor: Philippe Dreuw)
   Presentation: Monday, July 16, 2007, 9:00h
   
   List of references:
   
   • N. Cristianini, J. Shawe-Taylor: An Introduction to Support Vector Machines and Other Kernel-based Learning Methods, Section 3, Cambridge University Press, 2004.
   • J. Shawe-Taylor, N. Cristianini: Kernel methods for pattern analysis Cambridge University Press, Section 2 and 3, 2004.
   • B. Schölkopf, A. Smola: Learning with Kernels , MIT Press, London, 2002.
   
   
2. Introduction to Support Vector Machines (Look; Supervisor: Philippe Dreuw)
   Presentation: Monday, July 16, 2007, 10:00h
   
   List of references:
   
   • N. Cristianini, J. Shawe-Taylor: An Introduction to Support Vector Machines and Other Kernel-based Learning Methods, Section 6, Cambridge University Press, 2004.
   • B. Schölkopf, A.J. Smola, C.J.C. Burges (Hrsg.): Advances in kernel methods. Support vector learning MIT Press, 1999.
   
   
3. Introduction to MLP-based Features (Ewert; Supervisor: Christian Plahl)
   Presentation: Monday, July 16, 2007, 11:00h
   
   List of references:
   
   • Lei, Hwang, Ostendorf: Incorporating tone related MLP Posteriors in the future representation for Mandarin ASR, INTERSPEECH 2005
   • Stolcke, Morgan: Cross domain and cross language features estimated by Multilayer Perzeptron, ICASSP 2006
   • Chen, Zhu, Morgan: Learning Long-Term Temporal Features in LVCSR using neural networks, INTERSPEECH 2004 general Introduction: H. Bourlard and N. Morgan, Connectionist speech recognition a hybrid approach," in Kluwer Academic Press, 1994.
   
   
4. Introduction to Discriminative Training (Preuschl; Supervisor: Georg Heigold)
   Presentation: Monday, July 16, 2007, 12:00h
   
   List of references:
   
   • D. Povey and P. C. Woodland: Minimum Phone Error and I-Smoothing for Improved Discriminative Training. Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, 105 -- 108, vol. 1, 2002, Orlando, FL.
   • D. Povey: Discriminative Training for Large Vocabulary Speech Recognition. PhD thesis, Cambridge, England, 2004.
   • R. Schlüter: Investigations on Discriminative Training Criteria. Dissertation, Aachen, Germany, September 2000.
   
   
5. Maximum Entropy Methods (NN, Supervisor: Georg Heigold)
   
   List of references:
   
   • E. T. Jaynes: Information Theory and Statistical Mechanics. Phys. Rev., 106, 620, 1957.
   • evtl. Edwin T. Jaynes: Probability theory. The logic of science . Cambridge UP, 2003.
   • John Lafferty, Andrew McCallum, Fernando Pereira: Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. Proc. 18th International Conf. on Machine Learning, 2001.
   • Charles Sutton and Andrew McCallum: An Introduction to Conditional Random Fields for Relational Learning. MIT Press. 2006.
   
   
6. String Kernels (Gör; Supervisor: Daniel Stein)
   Presentation: Tuesday, July 17, 2007, 14:00h
   
   List of references:
   
   • E. Herbst, T. Joachims: SVMhmm Sequence Tagging with Support Vector Machines and its Application to Part-of-Speech Tagging, Cornell University, July 2006
   • J. Shawe-Taylor, N. Cristianini: Kernel methods for pattern analysis Cambridge University Press, Section 10 and 11, 2004.
   
   
7. Support Vector Machines for Hidden Markov Modeling (Bachwerk; Supervisor: Georg Heigold)
   Presentation: Tuesday, July 17, 2007, 15:00h
   
   List of references:
   
   • H. Lodhi, C. Saunders, J. Shawe-Taylor, N. Cristianini, C. Watkins: Text Classification using String Kernels, Journal of Machine Learning Research, 2:419-444, 2002.
   • Ganapathiraju, A., Support vector machines for speech recognition PhD Thesis, Mississipi State University, 2002.
   
   
8. Discriminative Alignment for Machine Translation (Belle; Supervisor: Arne Mauser)
   Presentation: Tuesday, July 17, 2007, 16:00h
   
   List of references:
   
   • Ben Taskar, Simon Lacoste-Julien, and Dan Klein: A Discriminative Matching Approach to Word Alignment. In Proc. HLT/EMNLP 2005, pp. 73--80, Vancouver, Canada, 2005.
   • Robert C. Moore: A Discriminative Framework for Bilingual Word Alignment. In Proc. HLT/EMNLP 2005, pp. 81-88, Vancouver, Canada, 2005.
   • Phil Blunsom and Trevor Cohn: Discriminative Word Alignment with Conditional Random Fields p. 65-72, ACL 2006, Sydney
   
   
9. Discriminative Training for Machine Translation (Jongiran; Supervisor: Arne Mauser)
   Presentation: Wednesday, July 18, 2007, 14:00h
   
   List of references:
   
   • Ben Taskar, D. Klein: Max-Margin Methods for NLP: Estimation, Structure, and Applications. Tutorial presented at ACL 2005, Ann Arbor, MI, June 2005.
   • Percy Liang, Alexandre Bouchard-Côté, Dan Klein, and Ben Taskar: An End-to-End Discriminative Approach to Machine Translation, p. 761-768, ACL 2006, Sydney
   • Christoph Tillmann and Tong Zhang: A Discriminative Global Training Algorithm for Statistical MT, p. 721-728, ACL 2006, Sydney
   
   
10. Maximum Entropy for Machine Translation (Guta; Supervisor: Daniel Stein)
    Presentation: Wednesday, July 18, 2007, 15:00h
    
    List of references:
    
    • Adam L. Berger, Stephen A. Della Pietra, Vincent J. Della Pietra: A Maximum Entropy Approach to Natural Language Processing, In Computational Linguistics, 1996.
    • Abraham Ittycheriah, Salim Roukus: A Maximum Entropy Word Aligner for Arabic-English Machine Translation In Proc. HLT/EMNLP 05, pp. 89--96, Vancouver, Canada, 2005.
    • I. Varea, F. Och, H. Ney and F. Casacuberta: Refined Lexicon Models for Statistical Machine Translation using a Maximum Entropy Approach , Associtation for Computational Linguistics, pp. 204--211, USA, 2001.
    • A. Ittycheriah, S. Roukus: Direct Translation Model 2, Proc. of NAACL HLT 2007, pp. 57-64, 2007.
    
    
11. Maximum Entropy for Speech Recognition (Tihar; Supervisor: Christian Plahl)
    Presentation: Wednesday, July 18, 2007, 16:00h
    
    List of references:
    • W. Macherey and H. Ney: A comparative study on maximum entropy and discriminative training for acoustic modeling in automatic speech recognition. Proc. European Conference on Speech Communication and Technology (ICSLP), Geneva, Switzerland, 2003.
    • M. K. Omar and M. Hasegawa-Johnson: Maximum Conditional Mutual Information Projection for Speech Recognition. Proc. of the Int. Conf. on Spoken Language Processing (ICSLP), Geneva, Switzerland, 2003.
    • D. Povey, B. Kingsbury, L. Mangu, G. Saon, H. Soltau and G. Zweig: fMPE: Discriminatively Trained Features for Speech Recognition. Proc. of the Int. Conf. on Acoutics, Speech, and Signal Processing (ICASSP), Philadelphia, PA, 2005.
    
    
12. Maximum Entropy for Language Modeling (NN; Supervisor: Stefan Hahn)
    • Ronald Rosenfeld: Two Decades of Statistical Language Modeling: Where do we go from here? Proc. of IEEE, 88(8):1270--1278, 2000 (speziell: Abschnitt ueber ME/exp. models)
    • Sehr gute Uebersicht und Literaturrefferenzen auf den Webpages von Zhang Le:
      • http://homepages.inf.ed.ac.uk/s0450736/maxent.html
      • http://homepages.inf.ed.ac.uk/s0450736/slm.html
    • Speziell zu LM mit ME: Ronald Rosenfeld: Adaptive Statistical Language Modeling: A Maximum Entropy Approach. PhD Thesis, CMU Pittsburgh, PA, 1994

Guidelines for the article and presentation:

• Online LaTeX-Documentation:

• LaTeX: "A document preparation system"
• LaTeX help 1.1
• The Not So Short Introduction to LaTeX
  
• LaTeX 2e for authors

• Document Templates:

• Article Template (164kB),  contains the template and all necessary files in tar format (or here 53kB in zip format).
• Presentation Slide Template (4.9MB), a zip file containing the template and all necessary graphics as well as the institute’s style template.

• Guidelines for articles and presentation slides:

• The aim of the seminar for the participants is to learn the following:
• to tackle a topic and to expand knowledge
• to critically analyze the literature
  
• to hold a presentation
  
• Take notice of references to other topics in the seminar and discuss topics with one another!
  
• Take care to stay within your own topic. To this end participants should be aware of the other topics in the seminar. If applicable, cross-reference other articles and presentations.
  

• Important: As part of the introduction, a slide should outline the most important literature used for the presentation. In addition, the presentation should clearly indicate which literature the particular elements of the presentation refer to.
  
• Take notice of references to other topics in the seminar and discuss topics with one another!
  
• Participants are expected to seek out additional literature on their topic. Assistance with the literature search is available at the faculty’s library. Access to literature is naturally also available at the Lehrstuhl für Informatik 6 library.
• Notation/Mathematical Formulas: consistent, correct notation is essential. When necessary, differing notation from various literature sources is to be modified or standardized in order to be clear and consistent. The lectures held by the Lehrstuhl für Informatik 6 should provide a guide as to what appropriate notation should look like.
  
• Tables must have titles (appearing above the table).
• Figures must have captions (appearing below the figure).
  
• In the case that no adequate translation of an English technical term is available, the term should be used unchanged.
• Articles and presentation slides can also be prepared in English.
  
• Completeness: acknowledge all literature and sources.
  
• Referencing must conform to the standard described in the article template.
• Examples should be used to illustrate points.
• Examples should be as complex as necessary but as simple as possible.
• Slides should be used as presentation aids and not to replace the role of the presenter; specifically, slides should:
• illustrate important points and relationships;
• remind the audience (and the presenter) of important aspects and considerations;
  
• give the audience an overview of the presentation.
  
• Slides should not contain chunks of text or complicated sentences; rather they should consist of succinct words and terms.
• Use illustrations where appropriate - a picture says a thousand words!
• Abbreviations should be defined at the first usage in the manner demonstrated in the following example: "[...] at the Rheinisch-Westfälischen Technischen Hochschule (RWTH) there are [...]".
  
• Take care to stay within your own topic. To this end participants should be aware of the other topics in the seminar. If applicable, cross-reference other articles and presentations.
• Usage of fonts, typefaces and colors in presentation slides must be consistent and appropriate. Such means should serve to clarify points or relationships, not be applied needlessly or at random.
  
• Care should be taken when selecting fonts for presentation slides (also within diagrams) to ensure legibility on a projector even for those seated far from the screen.
• 
  

Registration for the seminar:

Registration for the seminar  is only possible online via the registration page  provided by the institute. A link can be found on the Computer Science Department's homepage.

Inquiries relating to organizational aspects of the seminar should be directed to:

Room 6125b (1. Etage E2)
Telephone: 0241 / 80 21 612
E-Mail: schlueter@cs.rwth-aachen.de