Instructor: Robert C. Berwick	TA: Sourabh Niyogi
Email: berwick@ai.mit.edu	Email: niyogi@mit.edu
Office: 35-423	Office: 35-317
Phone: (617) 253-8918	Phone: (617) 253-1467
Office hours: Weds 12-2 and by appointment	Office hours: TBA shortly

New on this course's web pages:

•     02/06/02    This is the first announcement.  PC-Kimmo documentation is available in class and here.
•     02/06/02    Please fill out this questionnaire on your background/interests to help us guide the course .  (You should print it out.  It's not an on-line questionnaire.
•     02/06/02    Supplementary notes (pdf) for an overview of natural language processing to be read in conjunction with Lecture 1, available here.

Older messages:
• None so far

Prerequisites & Relation to Other Courses:

The material covered in this course is selected in such a way that at its completion you should be able to understand current papers in the field of Natural Language Processing (NLP).   No background in NLP is necessary.  All lectures will be published on this page in powerpoint (ppt), Adobe pdf (pdf) and postscript (ps) form; the latter two are more useful for downloading and printing. If you do not have Adobe Acrobat Reader for pdf files on your computer, you can download it from www.adobe.com.

Readings:

Required (available at the MIT Coop,  and through Quantum books):

 

Recommended & Reference Readings (all on library reserve):

 

Manning, C. D. and H. Schütze: Foundations of Statistical Natural Language Processing. The MIT Press. 1999. ISBN 0-262-13360-1.


 

Barton, E., Berwick, R., & Ristad, E.. Computational Complexity and Natural Language: The MIT Press. 1987. ISBN 0-26-02266-4. (Sorry no real cover picture available.)

Allen, J.: Natural Language Understanding. The Benajmins/Cummings Publishing Company Inc. 1994. ISBN 0-8053-0334-0.

Brady, J & Berwick, R.: Computational Models of Discourse. The MIT Press, 1983. ISBN-0-262-02183-8 .

Charniak, E.: Statistical Language Learning. The MIT Press. 1996. ISBN 0-262-53141-0.

• 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)

Assignments & Due Dates:

Assignments

This course is lab-oriented; that is, the work of the course is done via a series of laboratory exercises.  These will be handed out once approximately every two weeks.  There are no exams, in particular, there will be no final exam.  The final project will involve an element of non-determinism, i.e., so-called 'free will',  in that you will be able to choose your own project and combine elements from the previous laboratories, or do something completely new.  For the final project, we will have people work in teams of 2 or 3 (but not more).

The laboratory exercises are designed to be carried out on Athena.  If you are clever and adventuresome, you are certainly free to download the software used and get it running on your own PC/laptop, but this must be own 'your own nickel' - i.e., we cannot guarantee that you will succeed, nor can we offer technical support to do so.

Turning in the Assignments

When

The assignments are due at the end of class on the due date, i.e., 11:30am.

Policies

Lateness

You have up to 30 (thirty) late days to use up, that can be distributed among your laboratory projects. However, the last project must be turned during the last week of class (5/14-5/18), even if you have not used all of your days by then.

Once you use up your late days, late projects will not earn any points, even though they might be considered in borderline cases for the final grade. Thus try to turn in all projects, even though you might feel they are not to be counted. If you do not turn in a final (joint) project, you will receive an I (incomplete) for the class, and will have to make this up by next term (the incomplete will note that 80% of the coursework has been completed).

Cooperative Work and Plagiarism

Cooperative work is strongly encouraged; you are free to work together on laboratory assignments.  However, aside from the last project, you must write up and turn in your own work.  Please write the names of the people with whom you worked at the top of the first page.  Exact copies of laboratory reports will not be acceptable. (Something other than your name and those of your co-workers must be different!)  The aim of the course (and its pedagogical philosophy) is to learn about natural language processing.  You will learn more if you actually do the laboratory assignments.

The Assignments

Additional resources:

• Lab 1a: englex.tar.gz. (english rules and lexicon)
• Lab 1b: web version of Brill tagger with tracing option (watch out: default language is Swedish): here.
• Guest athena form http://web.mit.edu/accounts/Forms/guest-request.txt

Tentative Course Schedule:

Grading Weights: