2025 (Current Year) Faculty Courses School of Computing Department of Mathematical and Computing Science Graduate major in Artificial Intelligence
Natural Language Processing
- Academic unit or major
- Graduate major in Artificial Intelligence
- Instructor(s)
- Yuki Arase
- Class Format
- Lecture
- Media-enhanced courses
- -
- Day of week/Period
(Classrooms) - Class
- -
- Course Code
- ART.T459
- Number of credits
- 200
- Course offered
- 2025
- Offered quarter
- 3Q
- Syllabus updated
- Mar 31, 2025
- Language
- English
Syllabus
Course overview and goals
This course provides an introduction to the field of natural language processing (NLP), introducing fundamental concepts and techniques for processing human languages by computers. The course covers the linguistic background necessary for NLP, machine learning basics, text embedding, language modelling, text generation, and applications of NLP.
Linguistic competence is believed to be the most prominent human nature that distinguishes humans from other animals. This course aims to provide students with the ability to utilise fundamental NLP techniques to build language-related application systems, such as information extraction, question answering and dialogue systems.
Course description and aims
At the end of the course, students should be able to
(1) explain basic concepts of natural language processing and
(2) build sample application programs based on the above concepts.
Keywords
computational linguistics, corpus linguistics, language resources, text generation, language models, text embedding
Competencies
- Specialist skills
- Intercultural skills
- Communication skills
- Critical thinking skills
- Practical and/or problem-solving skills
Class flow
Students must prepare the specified section in the textbook. The former part of the course introduces NLP techniques based on the textbook. The latter part of the course is led by students: presentations of research papers followed by discussions.
Course schedule/Objectives
| Course schedule | Objectives | |
|---|---|---|
| Class 1 | N-gram Language Models | Specified in the class. |
| Class 2 | Naive Bayes, Text Classification, and Sentiment | Specified in the class. |
| Class 3 | Logistic Regression | Specified in the class. |
| Class 4 | Vector semantics and embeddings | Specified in the class. |
| Class 5 | Neural Networks | Specified in the class. |
| Class 6 | Transformers | Specified in the class. |
| Class 7 | Large Language Models | Specified in the class. |
| Class 8 | Model Alignment, Prompting, and In-Context Learning | Specified in the class. |
| Class 9 | Research paper presentations by students (1) | Specified in the class. |
| Class 10 | Research paper presentations by students (2) | Specified in the class. |
| Class 11 | Research paper presentations by students (3) | Specified in the class. |
| Class 12 | Research paper presentations by students (4) | Specified in the class. |
| Class 13 | Research paper presentations by students (5) | Specified in the class. |
| Class 14 | Research paper presentations by students (6) | Specified in the class. |
Study advice (preparation and review)
Students must read the assigned chapters and research papers before attending each class.
Textbook(s)
Jurafsky, D. & Martine, J. H.: Speech and Language Processing (3rd ed.), Prentice Hall (2023+). (https://web.stanford.edu/~jurafsky/slp3/)
Reference books, course materials, etc.
None.
Evaluation methods and criteria
Contribution to the class discussion (50%)
Presentation (50%)
Related courses
- ART.T548 ： Advanced Artificial Intelligence
Prerequisites
Basic understanding of Linear Algebra and Probability and Statistics
Other
None.