PFL043 Syllabus: Statistical NLP (2002/2003)
[Statistické metody zpracování přirozených jazyků, 2002/2003]
ZS 2/2 Z,Zk LS 2/2 Z,Zk
When: Thu 14:30 - 17:10
| Instructor: Jan Hajic |
| Email: hajic@ufal.mff.cuni.cz |
| WWW: http://ufal.ms.mff.cuni.cz/~hajic |
| Office: MFF UK Malostranske nam., 2nd floor, rm 66 |
| Phone: +420 221 914 257 |
| Office hours: Thu 13:00-14:00 |
New on this course's web pages:
- 11/01/02 These pages are still temporary. Please visit http://www.cs.jhu.edu/~hajic/courses/cs465/syllabus.html for the complete Hopkins syllabus.
Prerequisites & Relation to Other Courses:
Students should have a substantial programming experience in either C, C++, Java and/or Perl, and have preferably taken Data Structures (Datove struktury, TIN005), Unix (SWI015), and Intro to Probability (MAI016) or their equivalents, even though all the probability theory needed will be re-explained. Knowledge of, or willingness to learn the basics of Perl as-you-go (and on your own) is also important. Part of the benefits of the course is that although the lectures will be given in Czech, all the materials are in English and all the current English terminology will be explained in order to facilitate reading of current NLP literature, which is almost exclusively in English.The material covered in this course is selected in such a way that at its completion you should be able to understand papers in the field of Natural Language Processing, and it should also make your life easier when taking more advanced courses either at UFAL MFF UK or elsewhere.
No background in NLP is necessary.
Readings:
Required:
-
Manning, C. D. and H. Schütze: Foundations of Statistical Natural Language Processing. The MIT Press. 1999. ISBN 0-262-13360-1.
-
Recommended & Reference Readings:
-
Three copies of Jurafsky's book are available at UFAL's library.
Jurafsky, D. and J. H. Martin: Speech and Language Processing. Prentice-Hall. 2000. ISBN 0-13-095069-6. -
Wall, L., Christiansen, T. and R. L. Schwartz: Programming PERL, 3rd ed.. O'Reilly. 1996. ISBN 0-596-00027-8. (Sorry no large cover picture available.) -
Allen, J.: Natural Language Understanding. The Benajmins/Cummings Publishing Company Inc. 1994. ISBN 0-8053-0334-0. -
Cover, T. M. and J. A. Thomas: Elements of Information Theory. Wiley. 1991. ISBN 0-471-06259-6. -
Charniak, E.: Statistical Language Learning. The MIT Press. 1996. ISBN 0-262-53141-0. -
Four copies of Jelinek's book are available at UFAL's library, but they are primarily reserved for those taking his course (PFL044).
Jelinek, F.: Statistical Methods for Speech Recognition. The MIT Press. 1998. ISBN 0-262-10066-5. -
Proceedings of major conferences (related to Natural Language Processing):
- ACL (Association of Computational Linguistics)
- European Chapter of the ACL
- COLING (International Committee of Computational Linguistics)
- ANLP (Applied Natural Language Processing, by ACL)
- ACL SIGDAT, SIGNLL other SIG (Special Interest Groups) Workhops, such as WVLC (Workshop on Very Large Corpora)
- EMNLP (Empirical Methods in Natural Language Processing
- DARPA HLT (Defense Advanced Research Project Agency Human Language Technology Workshops)
-
Other Resources:
- CLSP Workshops: Language Engineering for Students and Professionals Integrating Research and Education
Assignments & Due Dates:
Unix lab accounts
For MFF UK students, please see http://www.ms.mff.cuni.cz/labs/unix. For others, please visit http://www.ms.mff.cuni.cz/students/externisti.html.Turning in the Assignments
How (technically)
-
Use a separate directory for each assigment. Create a main web page
called index.html or index.htm in
that directory. Create as many other web pages as necessary. Put all
the other necessary files (.ps files, pictures, source code, ...)
into the same directory and make relative links to them from your main
or other linked web pages. If you use some "content creation" tools
related to MSFT software please make sure the references use the
correct case (matching uppercase/lowercase).
- Pack everything into a single .tgz file:
cd <your assignment #x directory>
tar -czvf ~/assignx.tgz ./* Send the resulting file by e-mail (as an attachment) to
hajic@ufal.mff.cuni.cz
with the following subject line:
Subject: <your name in the form (no accents): First.Last> <number of the assignment>
e.g.
Subject: Jan.Novak 2
for Jan Novák, turning in the second assignment.
The Assignments
| No. | Due date | Task | Resources |
|---|---|---|---|
| Dec. 02, 2002 | Exploring Entropy and Language Modeling | TEXTEN1.txt (large!) TEXTCZ1.txt (large!) | |
| Feb. 24, 2003 | Word Classes | TEXTEN1.txt (large!) TEXTCZ1.txt (large!) TEXTEN1.ptg (large!) TEXTCZ1.ptg (large!) | |
| Apr. 22, 2003 | Tagging | texten2.ptg (large!) textcz2.ptg (large!) | |
| May 16, 2003 | TBA |
| Open to submissions | Tentative | Closed to submissions |
Additional resources:
- Eric Brill's short guide to Perl.
Tentative Course Schedule:
For the moment, please see the last year's page to get an idea.
Grading Weights:
| Assignments (4) | 50% |
| Final exam | 50% |
The assignments will get points (100 points each max.). Therefore, the final exam will be valued at 400 points.
Exam:
| Exam | Date, Time | Where |
|---|---|---|
| Mid-term
( |
Dec. 5, 2002, 2-2:30 | 64, 2.p., MS |
| Final | TBA | TBA |
Both the mid-term and the final exams will be written (not oral), with about 6 major questions and some subquestions. You will have 30 minutes for the mid-term, and up to 2 hours for the final exam to write down the answers.
To get an idea of the type of exam questions, please see the questionaire for one of the previous year's midterm exam, again at original course page.
As stated above, your final grade (or pass/fail for PhD students) will be determined by both the final exam and your assignment results in a 50:50 ratio.
In special circumstances (long-term absence etc.), some other schedule and grading scheme could be worked out individually, but please try hard to hand in all assignments in time and come for the final exam on the regular date.