CMSC 25020/35020, LING 28600/38600
This is a course in the Computer Science department, intended for upper-level undergraduates, or graduate students, who have good programming skills. There will be weekly programming assignments in Python. We will look at several current topics in natural language processing, and discuss both the theoretical basis for the work and engaging in hands-on practical experiments with linguistic corpora. In line with most current work, our emphasis will be on systems that draw conclusions from training data rather than relying on the encoding of generalizations obtained by humans studying the data. As a consequence of that, in part, we will make an effort not to focus on English, but to look at a range of human languages in our treatments.
CMSC 12200, 15200, or 16200 is a prerequisite, except in the case of graduate students.