Course Info for Ling 848/CMSC 828R, Fall 2004
Course Info for Ling 848/CMSC 828R, Fall 2004
Seminar in Computational Linguistics
Class mailing list
The class mailing list, which includes a weekly archive of postings,
is at
http://lists.umiacs.umd.edu/mailman/listinfo/nlpseminar.
Essentials
- Instructor:
Philip Resnik.
- Location and time of the class:
Marie Mount Hall 3418, Thursday, 2-5pm.
- Text: Weekly readings listed in the schedule of topics. Most of these are
available on the Web; any others will be made available in the
Linguistics Department course readings folders.
- Office hours: by appointment.
What's the Plan?
See the schedule of topics.
What's the course about?
This is an advanced seminar in computational linguistics / natural
language processing. We will focus on topics that are fast becoming
essential in order to follow the most up to date work in NLP, which
means a strong emphasis on statistical NLP models and methods. The
syllabus is not yet finalized, but I expect it to include, among other
topics, expectation/maximization (EM) algorithms, Bayesian modeling,
maximum entropy models, weighted finite-state transducers, etc., with
possible excursions into emerging areas such as semantic role labeling
and using the Web as a source of evidence.
Although the majority of time will be spent reading and discussing
relevant papers, I am also hoping to pull together a suite of software
that we can use to get some hands-on experience, e.g. language
modeling toolkits, the AT&T FST tools, etc.
The prerequisite is Ling645/CMSC723 or equivalent. Please feel free
to contact me with any questions, and feel free to suggest the course
to anyone who might be interested.
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.
- Class assignments:
Students will regularly write short reaction pieces in response to
readings. There will also be hands-on assigments designed to
give students the opportunity to work with models and algorithms
discussed in class.
- Class presentations:
Up to twice during the semester, each student will take responsibility for
an article (or related articles), discuss the material with the instructor,
and lead class discussion of the material and reactions to it.
- Final project:
Students will do a final implementation and/or computational
experimentation project using models and algorithms discussed in class.
Details TBD.
- Class participation: contribution to class discussions
will also be a factor in evaluating performance in the course.
Preparedness is essential.
What's the Plan?
The schedule of topics.
Philip Resnik, Associate Professor
Department of Linguistics and Institute for Advanced Computer Studies
Department of Linguistics
1401 Marie Mount Hall UMIACS phone: (301) 405-6760
University of Maryland Linguistics phone: (301) 405-8903
College Park, MD 20742 USA Fax: (301) 314-2644 / (301) 405-7104
http://umiacs.umd.edu/~resnik E-mail: resnik AT umd.edu