KAIST AI605 - Deep Learning for NLP (Spring 2022)
Links
Time & Location
Tue & Thu 09:00-10:15 at KAIST Seoul Campus Suite 9509 or via Zoom
- Visit KLMS or email a TA (or the instructor) for the Zoom invitation
- The class will be on-site and virtual hybrid; Seoul Campus students are expected to be on-site for the lectures. All lab sessions are fully virtual and via Zoom.
- All classes and materials will be in English.
Instructor
Minjoon Seo
-
Office: KAIST Seoul Campus Building 9 Room 202
-
Office Hours: Request via Calendly
TAs
Miyoung Ko
- miyoungko@kaist.ac.kr
- Head TA
Yongrae Jo
Joel Jang
Grading Policy
There is no exam in this class, and the final grade has the following breakdown:
- Assignments: 80% or 40%
- Project: 0% or 40%
- Attendance: 10%
- Participation: 10%
Note that you can choose either (1) complete all the four assignments, or (2) complete the first two assignments and complete the project (recommended if you are already working on an NLP project towards a publication). You will need to make the decision by the deadline of the third assignment.
The final grade will be determined by the following policy (after rounding to the nearest integer in percent):
- 97% to 100%: A+
- 93% to 96%: A0
- 90% to 92%: A-
- 87% to 89%: B+
- 83% to 86%: B0
- 80% to 82%: B-
- 77% to 79%: C+
- 73% to 76%: C0
- 72% or lower: C- or lower (fail)
Late Submission Policy
- We will give you 7 no-penalty late days that can be used across all assignments (but not the final project).
- You need to explicitly mention how many late days you will be using for each submission. We will assume no late day is used if not mentioned in your submission.
- After you used all late penalty days, there will be -10% penalty for every late day (24 hours). That is, if the assignment or the project is due at 11pm and you submit at 11:30pm on the next day, 20% will be deducted.
- Note that you can achieve higher than 100% (with bonus questions), which will allow you to make up for other lower grades.
- An assignment that is more than 7 days late will not be accepted and you will receive 0% for that assignment.
Course Description
This course covers recent advances in natural language processing area driven by deep learning. Topics include (but are not limited to)
- Recurrent Neural Networks
- Encoder-Decoder
- Transformer
- Language Model
- Pretrained Language Model (e.g. BERT)
- Text Classification (e.g. Sentiment Analysis)
- Sequence Tagging (e.g. NER, Question Answering)
- Sequence Generation (e.g. Summarization, Machine Translation, Semantic Parsing)
- Zero-shot Learning (e.g. GPT-3)
- Modern NLP Libraries (e.g. Hugging Face)
Project
The deliverable for the project will be a 4-to-8-page paper in ACL format that will be submitted to a conference on or after Feb 28, 2022 (i.e. the first day of the semester). That is, you cannot use a paper that was previously submitted. This option is for you to put more time on your own work if you are alrady working on an NLP-related project, so please do not exploit it in a bad way!
Textbook
There is no required textbook for this course but I highly recommend Speech & Language Processing, whose pdf version is available for free, for your reference.