DSC8006 : Natural Language Processing (NLP) and Generative AI
- Offered for Year: 2025/26
- Module Leader(s): Dr Stephen McGough
- Lecturer: Dr Huizhi Liang
- Owning School: Mathematics, Statistics and Physics
- Teaching Location: Newcastle City Campus
Semesters
Your programme is made up of credits, the total differs on programme to programme.
| Semester 2 Credit Value: | 20 |
| ECTS Credits: | 10.0 |
| European Credit Transfer System | |
Aims
• Introducing the fundamentals of Natural Language Processing () and Large Language Models (LLMs)
within Generative AI and their impact across various sectors.
• The core concepts behind these areas NLP and LLMs.
• Applications of NLP and LLMs in real world scenarios.
• The standard toolkits used for NLP and LLMs.
• How to appropriately apply these toolkits to real-world problems.
• Make students fluent in the approaches of NLP and LLMs which will allow them to build up the skills
to enable them to apply these skills for applications in companies, academia or the third sector.
• Know the limits and ethical impacts of using such tools to enable them to make appropriate decisions
when working.
• Make students aware of good practices and how to ensure their results are reported in a fair and
honest manner
Outline Of Syllabus
Material will cover such topics as, whilst also including new and emerging areas of research:
• Introduction
• Regular expressions, word tokenisation, text-preprocessing
• Part-of-Speech Tagging
• Text classification
• Information Extraction: Named Entity Recognition
• Sequential models (RNN, LSTM)
• Semantics
• Word vectors and language models
• Syntactic Parsing
• Question Answering and Summarisation
• Architecture engineering and scaling law - Transformer and beyond
• Training LLM - Pre-training, Fine Tuning
• Evaluation and benchmarking
• How to Use and Adapt LLMs (decoding, prompting)
• Generative AI
• Multi-modal models
• Retrieval Augmented Generation (RAG)
• Reasoning and Planning
• Model compression
• Agentic AI: agent, tool use
• Alignment and limitations
• Problems & Risks
Teaching Methods
Teaching Activities
| Category | Activity | Number | Length | Student Hours | Comment |
|---|---|---|---|---|---|
| Guided Independent Study | Assessment preparation and completion | 1 | 0:30 | 0:30 | Oral Examination |
| Guided Independent Study | Assessment preparation and completion | 1 | 4:30 | 4:30 | Preparation for oral examination |
| Guided Independent Study | Assessment preparation and completion | 1 | 30:00 | 30:00 | Preparation and completion of the LLM assignment |
| Guided Independent Study | Assessment preparation and completion | 1 | 30:00 | 30:00 | Preparation and completion of the NLP / Generative AI assignment |
| Guided Independent Study | Assessment preparation and completion | 11 | 2:00 | 22:00 | Lecture follow-up includes time for the formative practical/tutorial exercises |
| Guided Independent Study | Directed research and reading | 22 | 1:00 | 22:00 | Pre-recorded online materials to aid learning |
| Scheduled Learning And Teaching Activities | Practical | 24 | 1:00 | 24:00 | Practical sessions (In-person) |
| Scheduled Learning And Teaching Activities | Small group teaching | 22 | 1:00 | 22:00 | Tutorial sessions (in-person) |
| Scheduled Learning And Teaching Activities | Drop-in/surgery | 2 | 1:00 | 2:00 | Practical sessions (in-person) |
| Guided Independent Study | Independent study | 1 | 43:00 | 43:00 | Independent background reading |
| Total | 200:00 |
Teaching Rationale And Relationship
Lectures materials are used for the delivery of theory and explanation of methods, illustrated with examples, and for giving general feedback on marked work.
Lecture follow-up, e.g., quizzes and exercises, is associated with each lecture to provide sufficient hands-on training and rapid feedback on understanding.
Scheduled sessions are used both for solution of problems and work requiring extensive computation to give insight into the ideas/methods studied
Assessment Methods
The format of resits will be determined by the Board of Examiners
Other Assessment
| Description | Semester | When Set | Percentage | Comment |
|---|---|---|---|---|
| Practical/lab report | 2 | M | 50 | NLP / Generative AI assignment (max 1000 lines of code) |
| Practical/lab report | 2 | M | 50 | LLM assignment (max 1000 lines of code) |
Zero Weighted Pass/Fail Assessments
| Description | When Set | Comment |
|---|---|---|
| Oral Presentation | M | Presentation and demonstration of the methods and results from the practical/lab reports (30 mins) |
Formative Assessments
Formative Assessment is an assessment which develops your skills in being assessed, allows for you to receive feedback, and prepares you for being assessed. However, it does not count to your final mark.
| Description | Semester | When Set | Comment |
|---|---|---|---|
| Prob solv exercises | 2 | M | Practical/Tutorial exercises. Approx one per practical session |
Assessment Rationale And Relationship
The assignments test the students’ ability to apply NLP and LLM techniques in a reproducible manner, using effective tools and methods to solve a real-world challenge.
The oral exam is a pass/fail component to validate that the student has understood the key aims of the module.
The formative assessment facilitates a reflective learning. The 'teachers' answer to each exercise is released two weeks after assessment is set with students expected to talk within the practical session about anything which is not understand how their answer differs
Reading Lists
Timetable
- Timetable Website: www.ncl.ac.uk/timetable/
- DSC8006's Timetable