COMS 6998: Computational Models of Speech and Language

Instructors
Michelle Levine
mlevine[at]cs[dot]columbia[dot]edu
Office hour: Wednesday, 3-4 (7LW3 CEPSR/Shapiro)

Sarah Ita Levitan
sarahita[at]cs[dot]columbia[dot]edu
Office hour: Tuesday, 11-12 (7LW3 CEPSR/Shapiro)

Teaching Assistants
Nishi Cestero
nishi[at]cs[dot]columbia[dot]edu
Office hour: Monday, 2-3 (7LW3 CEPSR/Shapiro)

Zixiaofan (Brenda) Yang
brenda[at]cs[dot]columbia[dot]edu
Office hour: Thursday, 11-12 (7LW3 CEPSR/Shapiro)

Time: Thursdays 4:10pm-6:00pm
Location: 304 Hamilton Hall
Prerequisite: COMS 3133/4/7/9 (Data Structures) or equivalent programming ability in at least one systems or scripting language (C++, Java, Python)

Description
Computational Models of Speech and Language is a seminar in NLP and speech processing. This course introduces students to research and data analysis techniques in computational linguistics and psychology. Each week we will cover a topic in psychology that can be approached using computational models. Throughout the course, we will introduce a variety of speech and statistical tools that can be used to analyze spoken language and we will demonstrate how speech technologies can be applied in the real world. Topics include personality, deception, trust, depression, dementia.

Grade Breakdown

• 20% Class participation

10% discussion board posts
5% leading discussion board
5% attendance and in-class participation

Students will be expected to complete all reading assignments before class and to actively participate in class discussions. Each week, students will complete at least 2 postings to a discussion board on CourseWorks. In addition, each student will be in charge of managing the online discussion board for one week. More details can be found here.

• 20% Data assignments

There will be two assignments in which students will apply data analysis techniques to natural language data.

• 15% Final project proposal and literature review


• 5% Final project presentation

Students will present their final project as a pitch to the class.

• 40% Final project

The final project will involve designing and implementing a computational approach to solving a problem in speech or text processing. Students will submit a final paper along with code and data.

Absence policy: An unexcused absence will give you a zero for participation for that day. An excused absence will have no participation penalty. Absences must be cleared with the professors in advance of the class being missed. Weekly postings are required even if you miss a class.

Academic Integrity
The SEAS academic integrity policy is found here.
The CS academic integrity policy is found here.

Syllabus
Note: Schedule and readings are subject to change