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
- Bachelor students: Einführung in das wissenschaftliche
Arbeiten (Proseminar)
- Master students: Bachelor degree
- Diploma students: Vordiplom
- Attendance of at least one of the lectures Pattern Recognition
and Neural Networks, Introduction to Statistical Classification,
Automatic Speech Recognition, or Statistical Methods in Natural
Language Processing, or evidence of equivalent knowledge.
- For successful participants of the above lectures, the
possibility of a seminar talk is guaranteed.
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.
- Proposals: initial proposals (report's content
page) have to be submitted by email to your supervisors by Oct. 6, 2014. At this time
participants must arrange an appointment with the individual
supervisor.
- Article: must be submitted at least 1 month prior
to the trial presentation date, but not later than
Nov. 17, 2014 to the individual supervisor in electronic form
(PDF).
- Presentation slides: must be submitted at least
1 week prior to the trial
presentation date to the individual supervisor in
electronic form (PDF).
- Trial presentations: at least 2 weeks prior to the
actual presentation date. Please refer to your individual
supervisor to schedule your trial presentation.
- Seminar presentations:will be scheduled after
the kick-off meeting, see comments above on seminar mode.
- Final (corrected) articles and presentation slides:
must be submitted 2 weeks
after the presentation date at the latest to the
individual supervisor in electronic form (PDF).
- Compulsory attendance: in order to receive a
certificate participants must attend all presentation
sessions.
- Ethical Guidelines:The Computer Science
Department of RWTH Aachen University has
adopted ethical
guidelines for the authoring of academic work such as
seminar reports. Each student has to comply with these
guidelines. In this regard, you, as a seminar attendant, have
to sign
a declaration of
compliance, in which you assert that your work complies
with the guidelines, that all references used are properly
cited, and that the report was done autonomously by
yourself. We ask you do download
the guidelines
and submit
the declaration
together with your seminar report and talk to your individual
supervisor. You also find
a German
version of the guidelines and
a German version of
the declaration you may use as well.
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:
- 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.
- 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.
- 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.
- Hierarchical Phrase-based Machine Translation (Timmermanns; Supervisor: Stephan Peitz)
References:
- D. Chiang: "Hierarchical Phrase-Based Translation," Computational Linguistics, Vol. 33(2), pp 201-228, June 2007.
- 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.
- Lightly-Supervised Training for Statistical Machine Translation (Hamadache; Supervisor: Malte Nuhn)
References:
- H. Schwenk: "Investigations on Large-Scale Lightly-Supervised Training for Statistical Machine Translation," in Proc. IWSLT, pp. 182-189, Waikiki, Hawaii, USA, October 2008.
- Large Scale Parallel Document Mining for Machine Translation (Frohn; Supervisor: Malte Nuhn)
References:
- J. Uszkoreit, J. Ponte, A. Popat, and M. Dubiner: "Large Scale Parallel Document Mining for Machine Translation," in Proc. COLING, pp. 1101-1109, Beijing, China, 2010.
- J. Smith, H. Saint-Amand, M. Plamada, P. Koehn, C. Callison-Burch, and A. Lopez: "Dirt Cheap Web-Scale Parallel Text from the Common Crawl," in Proc. ACL, Sofia, Bulgaria, August 2013.
- System Combination for Machine Translation (Wallraff; Supervisor: Markus Freitag)
References:
- E. Matusov et al.: "System Combination for Machine Translation of Spoken and Written Language," IEEE Transactions on Audio, Speech and Language Processing, Vol. 16(7), pp. 1222-1237, September 2008.
- A. V. Rosti, N. F. Ayan, B. Xiang, S. Matsoukas, R. Schwartz, and B. Dorr: "Combining Outputs from Multiple Machine Translation Systems," in Proc. NAACL, Rochester, NY, USA, April 2007.
- Deciphering Foreign Language (Richter; Supervisor: Malte Nuhn)
References:
- S. Ravi, and K. Knight: "Deciphering Foreign Language", in Proc. ACL, pp. 12-21, Portland, Oregon, USA, 2011.
Topics with prior knowledge:
- Operation Sequence Model (Graça; Supervisor: Andy Guta)
References:
- N. Durrani, A. Fraser, H. Schmid, and H. Hoang: "Can Markov Models Over Minimal Translation Units Help Phrase-Based SMT?," in Proc. ACL, Sofia, Bulgaria, August 2013.
- N. Durrani, A. Fraser, and H. Schmid: "Model With Minimal Translation Units, But Decode With Phrases," in Proc. NAACL, Atlanta, Georgia, USA, June 2013.
- Discriminative Training for MT (Vaitl; Supervisor: Joern Wübker)
References:
- S. Green, S. Wang, D. Cer, and C. D. Manning: "Fast and adaptive online training of feature-rich translation models," in Proc. ACL, pp. 311–321, Sofia, Bulgaria, August 2013.
- H. Yu, L. Huang, H. Mi, and K. Zhao: "Max-violation perceptron and forced decoding for scalable mt training," in Proc. EMNLP, pp. 1112–1123, Seattle, USA, October 2013.
- Word Alignment with Neural Network (Soliman; Supervisor: Jan-Thorsten Peter)
References:
- N. Yang, S. Liu, M. Li, M. Zhou, and N. Yu: "Word Alignment Modeling with Context Dependent Deep Neural Network," in Proc. ACL, Sofia, Bulgaria, August 2013.
- Neural Network in Decoding (Rossenbach; Supervisor: Jan-Thorsten Peter)
References:
- J. Devlin, R. Zbib, Z. Huang, T. Lamar, R. Schwartz and J. Makhoul: "Fast and Robust Neural Network Joint Models for Statistical Machine Translation," in Proc. ACL, Baltimore, Maryland, USA, June 2014.
- A. Vaswani, Y. Zhao, V. Fossum, and D. Chiang: "Decoding with Large-Scale Neural Language Models Improves Translation," in Proc. EMNLP, Seattle, USA, October 2013.
- 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.
- Syntax-based Machine Translation - String To Tree (Bretschner; Supervisor: Stephan Peitz)
References:
- P. Williams, and P. Koehn: "GHKM rule extraction and scope-3 parsing in Moses," in Proc. WMT, pp. 388-394, Montreal, Quebec, Canada, June 2012.
- M. Galley, M. Hopkins, K. Knight, and D. Marcu: "What's in a translation rule?", in Proc. NAACL, pp. 273-280, Boston, Massachusetts, USA, May 2004.
- Syntax-based Machine Translation - Tree To String (Schupp; Supervisor: Stephan Peitz)
References:
- G. Neubig, and K. Duh: "On the Elements of an Accurate Tree-to-String Machine Translation System," in Proc. ACL, Baltimore, Maryland, USA, June 2014.
- Y. Liu, Q. Liu, and S. Lin: "Tree-to-string alignment template for statistical machine translation," in Proc. ACL, pp. 609-616, Sydney, Australia, July 2006.
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.
- Online LaTeX-Documentation:
- Guidelines for articles and presentation slides:
General:
- 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.
Specific:
- 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
facultys library. Access to literature is naturally also available at
the Lehrstuhl 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 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.
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