CSC 594 Home
|
CSC 594 Topics in AI: Applied Natural Language
Processing
|
Time: | M 5:45 - 9:00 PM, Room CDM 202 |
Instructor: | Noriko Tomuro, tomuro@cs.depaul.edu |
Office: | CDM 648 (Loop; CDM building 6th floor) |
Phone: | (312) 362-5218 (Loop) |
Office Hours: | Mon: 4:45 - 5:45
PM Wed: 2:00 - 3:00 PM |
Course Description:
This is a project-based, seminar-style course on Natural Language Processing (NLP). Students will work with professors and (other) PhD students on several NLP-related research projects.
During the course, some foundational NLP concepts and tasks will be introduced in the first 2-3 weeks, then the students will be divided into groups where each group (of 2-3 students) will work on a project for the rest of the quarter. The class will meet every week to report progress and discuss/brainstorm ideas. Students will also present research papers which are assigned by the instructor.
Prerequisites:
Consent of the instructor. Although not required, the following courses are strongly recommended: CSC 578 (Machine Learning), CSC 575 (Information Retrieval), CSC 480 (Foundations of AI). Students are also expected to be proficient in at least one programming language (Java, C++, C, Lisp, SAS, MatLab etc.)
Textbook:
There is no required textbook for this course. However, the following books are highly recommended as references:
Grading:
The grade distribution is as follows:
Assignments 40%
Project 60%
The grading scale is as follows:
90-100 A 80-89.99 B 70-79.99 C 60-69.99 D 0-59.99 F
Plusses and minuses will be given at the high/low ends of each grade range (note: no A+'s).
Late Policy:
Assignments are due at 11:59 pm of the due dates. Late assignments are accepted (through email attachment) with the following penalty.
If assignment is turned in... | Penalty will be... |
---|---|
within 3 days of due date | 10% of the total points for each day it is late |
3 days or more after due date | will NOT be accepted |
Plagiarism/Cheating and Incompletes:
See the University and School policies on plagiarism and incompletes.