Course syllabus
A. Course Description:
This course deals with computer processing of human languages, including the use of neural networks and deep learning in natural language processing. The topics covered include: regular expressions, words and edit distance, n-grams, part-of-speech tagging, feed-forward neural networks, neural network training, word embedding, convolutional neural networks, recurrent neural networks, sequence-to-sequence models with attention, transformers, context-free grammars, syntactic parsing, semantics, and discourse.
B. Short Syllabus:
Please note that these times and dates are indicative. Please check Announcements here in Canvas for any updates.
The syllabus was last updated on 24 Mar 2024, to correct the project Final Report deadlines.
Date | Description and Optional Readings | Deadlines and Mark Weightage |
NUS Week 01 |
What is NLP? |
|
NUS Week 02 |
Words |
|
NUS Week 03 |
Language Models |
|
NUS Week 04 |
Text Classification |
|
NUS Week 05 |
Connectionist Machine Learning |
|
NUS Week 06 |
Embeddings and Ethics |
|
Week Recess | ||
NUS Week 07 |
Sequences |
|
NUS Week 08 |
Encoder–Decoder |
|
NUS Week 09 |
Trees |
|
NUS Week 10 |
Transformers (Friday Section 1 breaks this week due to Good Friday holiday) |
|
NUS Week 11 |
Applications |
|
NUS Week 12 |
Recent Developments in NLP: |
|
NUS Week 13 |
(No lectures; we miss Week 5 for L2 and Week 10 for L1) |
|
Reading Week |
|
|
Exam Week 1 |
|
|
C. Indicative Assessment Modality:
Please note that the below assessments and modalities are indicative. Please check Announcements here in Canvas for any updates. The instruction staff will endeavour not to change assessments unreasonably from these indicative settings.
- Final Exam: 30%
- 3 Individual Assignments: 30% (10% each)
- Group Project: 35% (5% Intermediate Update / 30% Final Report)
- Lecture, Tutorial, Project, Canvas Participation: 5%
Total 100%
Course summary:
Date | Details | Due |
---|---|---|