CS 4740 - Natural Language Processing

(crosslisted) COGST 4740 , LING 4474
(SMR-AS)

Fall. 4 credits. Student option grading (no audit).

At least three semesters of college-level, programming-intensive classes (e.g., completion of CS 3110 ) are very highly recommended. CS 2110 may suffice if you individually could have successfully and easily completed the assignments by yourself.
Strong python programming skills. CS 1133 does not suffice. Experience beyond CS 1110 /CS 1112 is highly recommended.
Experience with pytorch recommended.
Comfort with elementary probability.
One course in college-level linear algebra; clear understanding and facility with matrix and vector operations is a must.
Familiarity with differentiation at the level of a first college-level calculus course.
Machine learning is recommended but not required.

Co-meets with CS 5740.

L. Lee.

This course constitutes an introduction to natural language processing (NLP), the goal of which is to enable computers to use human languages as input, output, or both. NLP is at the heart of many of today’s most exciting technological achievements, including machine translation, question answering and automatic conversational assistants. The course will introduce core problems and methodologies in NLP, including machine learning, problem design, and evaluation methods.

This class satisfies the practicum/project requirement for CS majors. As a consequence, expect each of the roughly four connected programming assignments to take tens of hours, although this time is distributed over multiple weeks; to require writing code to massage raw-ish data into different formats and other accessory functions as well as to implement core algorithms; and to necessitate much independent examination of documentation.