LING 8570

Natural Language Processing Techniques

Offered every spring.


Information for Spring 2008:

Scheduled meeting time:
2:00-3:15 Tuesday/Thursday and 12:20-1:10 Friday.

Scheduled to meet in Room 531, Aderhold Hall,
but we will almost certainly meet in the Artificial Intelligence Center
(Conference room 110; enter through Room 111, Graduate Studies Research Center)

Instructor: Dr. Michael A. Covington, mc@uga.edu

Course web site: http://www.ai.uga.edu/mc/8570.html

Content: Basic principles of human language; structure of English from a computational point of view; algorithms and techniques for computer understanding of human language.

This is a "hands-on" implementation course for people who already know how to program in Prolog. If you do not know Prolog, it is absolutely impossible to take this course and you should consider taking LING 6570 instead.

Course goals: This course will be somewhat different from what we have done in past years (though similar to 2003-2005). We will concentrate on cooperatively producing some reusable software tools in SWI (ISO) Prolog. See http://www.ai.uga.edu/mc/pronto for past work of this type.

We will take the usual topics in a slightly different order than in earlier years. We will do tokenization and morphology first, then chunk parsing, then other types of parsing, and finally semantics.

Prerequisites:

Required textbook:

Optional textbooks:

Caution! If you order your books online, be sure to place the order at least 1 month before the course begins, because we will use the textbooks on the first day. Textbooks are also available at the University Bookstore next to the Tate Student Center on campus.

Requirements:

Academic honesty policy: The rules of the University apply to this course.
Note: All graded work is done individually; although projects are part of a larger effort, each project is done by a student working alone. Student projects in this course are published on the Web, so it is extremely important for them to be ready for the scrutiny of the entire scholarly world.