Course Info for CMSC723/LING723, Fall 2007
Course Info for CMSC723/LING723, Fall 2007
Computational Linguistics I
Class mailing list
Students registered for this courses should be on the cmsc723-0101-fall07@coursemail.umd.edu email list. Important announcements will be sent there.
Essentials
- Professor: Bonnie Dorr
Co-instructor: Nitin Madnani
TAs: Hamid Shahri and
Alexandros Tzannes
- Location and time of the class:
Computer
Science Instructional Center (CSIC) Room 2107 [MOVED to 2117 due to overheating!!!], Wednesdays, 4-6:30pm.
- Text:
Weekly readings listed in the schedule of topics are mostly from the second edition of
Dan Jurafsky and James Martin (to be published in 2007),
"Speech and Language Processing: An Introduction to Natural Language
Processing, Speech Recognition, and Computational Linguistics."
Although this edition is not yet available for purchase, you
may click here for the
updated
chapters.
- Syllabus:
See the schedule of topics.
- Office hours:
Bonnie Dorr: By appointment.
Hamid Shahri: AVW 1151 (usual TA room), Mondays, 1-3.
Alexandros Tzannes: AVW 1151 (usual TA room), Tuesdays, 12-2.
What's the course about?
This is the first semester in our two-semester graduate sequence in
computational linguistics. In the first semester, we will be
disussing fundamental methods in natural language processing, with a
focus on core representations and algorithms. Topics include:
finite-state methods, context-free and extended context-free models of
syntax; parsing and semantic interpretation; n-gram and Hidden Markov
models, part-of-speech tagging; natural language applications such as
machine translation, automatic summarization, and question answering.
Students completing this course will have a solid working knowledge of
the basics of NLP and will be well prepared for the second semester
course, which covers natural language processing with a focus on
corpus-based statistical techniques.
Students taking this course should be competent programmers, since
concepts taught in class will sometimes be reinforced in practice by
hands-on programming assignments. We are not assuming a great deal of
familiarity with linguistics; students needing to get up to speed on
linguistics concepts will do fine with Jurafsky and Martin's material
on word classes and context-free grammars for English (in new Chapters 5
and 12).
Please feel free to contact us with any questions, and feel free to
suggest the course to anyone who might be interested.
See the schedule of topics for
class-by-class plans.
How will the course be graded?:
Students will be evaluated on their ability to master the
content of the material in the course and to think
critically about ideas presented to them.
- Exams (50%): There will be a midterm exam (25%) and a
final exam (25%). These will be take-home exams.
CS MS comp grade (AI area) will be based entirely on the average of the two exams.
- Class assignments/projects (45%):
There will be five homework assignments, four of which are for
credit: 10% (assignment 2), 12.5% (assignment 3), 10% (assignment
4), 12.5% (assignment 5). These assignments may involve on-paper
exercises (e.g. walking through algorithms or calculations),
hands-on programming, or analysis of data.
- Class participation (5%):
Showing up for class, demonstrating preparedness, and contributing
to class discussions.
Policy for Incomplete Work
- Late assignments. If an assignment is late by
up to 24 hours, the grade will be reduced by 10%. By 48 hours, 20%.
And so forth. Exceptions can be discussed in cases of medical
excuses, family emergencies, equipment failure, etc., but being busy
is not a valid excuse, and the sooner you talk to us about a
problem the better.
There are several common problems that we are
unlikely to consider as valid reasons for failing to get
work in on time. These include (a) failure to manage your time
properly, (b) discovering an assignment is harder than you expected
it to be (see item a), and (c) losing code or data that should have
been backed up, unless it's someone else's fault.
- Late assignment exception. Each student can
ask to extend an assignment due date by 48 hours one time during
the semester, no questions asked.
- 'Incomplete' as a grade. We will not issue an
'incomplete' as a grade except for serious, valid reasons, generally
in the category of emergencies. See above for some reasons
unlikely to be considered valid. If you are having problems of any kind,
please talk to one of us as soon as possible.
Course Accounts
Class work will take place on Linux servers. User accounts and passwords will be distributed in class. Use the following to connect to the machine:
ssh username@linuxlab.csic.umd.edu
Then you will be prompted for the password.
Bonnie Dorr, Professor
Department of Computer Science and Institute for Advanced Computer Studies
A.V. Williams Building, 3153
University of Maryland
College Park, MD 20742 USA
URL: http://www.umiacs.umd.edu/~bonnie
Phone: (301) 405-6768
E-mail: bonnie AT umiacs _DOT.GOES.HERE_ umd _DOT.GOES.HERE_ edu