I’m very excited to create this new graduate course in Fall 2021! My aim is to make this course as inclusive, diversified, and open as possible, and I will co-list the course to several communities of students:
- AC295: Topics in Applied Computation, for IACS’ Master’s students
- CS287r: Deep Learning for NLP, for computer science concentrators
- CSCI E-115B Harvard Extension School, for the general public all around the world (online)
How can computers understand and leverage text data and human language? Natural language processing (NLP) addresses this question, and in this course students study the current, best approaches. This course provides students with a foundation of advanced concepts and requires students to conduct significant research on an NLP project of their choosing, culminating with a high-quality short paper (4 pages). Assessment also includes pop quizzes, homework assignments, and an exam. My goal is to help challenge each student to elicit one’s best, and along the way for the course to be one of the most fun and rewarding educational experiences.
|Chris Tanner (Instructor)||William Tong (TF)||Alexander Lin (TF)||Annie Zhu (CA)||Richard Qiu (CA)|
- Tuesdays and Thursdays @ 9:45am - 11am in SEC LL2.221 (Allston)
- Mon @ 1:30pm - 3:30pm: Alex (120 minutes) and Annie (~75 minutes)
- Wed @ 5pm - 7pm: Richard and William
- Thurs @ 2:30pm - 4:30pm: Chris
- Sun @ 10am - 11am: Annie (Zoom only)
- Foundation: Pop Quizzes: 10% (during lecture for in-person students)
- Foundation: Exam: 10% (during lecture for in-person students)
- Application: Homework Assignments: 30% (two weeks for each)
- Creating New Knowledge: Research Project: 50% (twelve weeks)
- Canvas: homework assignments
- EdStem (should access via Canvas): discussion, help, announcements, quizzes
- Project Ideas (coming soon): on-going spreadsheet to collaboratively find and create research projects
- Emergency Helpline: for private concerns, issues, and questions (not course content)
- Supplemental Resources: a compilation of useful, external resources
The demand for this course content is extremely high, and I’m thrilled to see so many curious students. Enrollment is now closed; I randomly selected 35 Harvard (non-DCE) students amongst those who have a strong foundation of the pre-reqs (per the course application form). I am also excited to have 20 Harvard DCE students join us remotely from around the world.
No prior NLP experience is expected or necessary, but students must have a basic foundation in probability and calculus, along with strong knowledge of Machine Learning. See the syllabus for more details, along with HW #0 (ungraded) to assess if your current knowledge is aligned with the pre-req expectations – you should be able to answer all of the questions without much difficulty.
CS187 vs CS287
Students interested in learning NLP should take either this course or Stuart Shieber’s CS187 (Introduction to Computational Linguistics and NLP), which is also offered this semester! I describe the differences here.
If you’re looking for AC295: Practical Data Science (MLOps), that course is currently being offered as AC215 by Pavlos Protopapas this semester! For context, AC295 is a “Topics in Applied Computation” course of revolving, cutting-edge content. In its inaugural offering, Spring 2020, it concerned Practical Data Science (MLOps). This semester, Fall 2021, AC295 will concern my new NLP course, and the highly desired MLOps course will be simultaneously offered as AC215.