Skip to main content

Module

DSC2008 : Natural Language Processing and Generative Models

  • Inactive for Year: 2026/27
  • Module Leader(s): Dr Huizhi Liang
  • Lecturer: Dr Xinhuan Shu, Dr Varun Ojha
  • Owning School: Computing
  • 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

This module develops your understanding of how intelligent systems process, represent, and generate human language using modern natural language processing and generative AI approaches. You will study methods for modelling text and language data, alongside approaches for tasks such as classification, information extraction, and text generation. The module also introduces agentic AI, exploring how language-based models can support reasoning, planning, interaction, and decision making within intelligent systems. The emphasis is on understanding system behaviour, evaluating performance, and applying language and generative AI methods critically and responsibly within practical contexts.

Outline Of Syllabus

Topics covered by this module include:

Text processing and preparation techniques
Topic modelling and document analysis
Text and language representations
Large language models and generative AI systems
Fine-tuning approaches and retrieval-augmented generation
Generative models, including GANs and diffusion models
Multimodal models and cross-modal representations
Sentiment analysis and opinion mining
Syntax and linguistic structure
Named entity recognition and information extraction
Agentic AI and language-based reasoning systems
Human–AI interaction and conversational systems
Prompt engineering and interaction design for generative AI
Ethical, societal, and professional considerations associated with generative AI systems
Evaluation methods and performance assessment for language and generative models
Applications of natural language processing and generative AI systems

Teaching Methods

Teaching Activities
Category Activity Number Length Student Hours Comment
Structured Guided LearningLecture materials201:0020:00Reading through lecture materials – preparing / follow up
Guided Independent StudyAssessment preparation and completion134:0034:00Preparation for and completion of summative LLM coursework
Scheduled Learning And Teaching ActivitiesLecture211:0021:00Lectures
Guided Independent StudyAssessment preparation and completion134:0034:00Preparation for and completion of summative NLP coursework
Guided Independent StudyAssessment preparation and completion151:0051:00Preparation for and completion of summative exam
Scheduled Learning And Teaching ActivitiesPractical201:0020:00Supervised practical sessions focused on hands on implementation
Guided Independent StudyDirected research and reading201:0020:00Wider reading as per provided reading list
Total200:00
Teaching Rationale And Relationship

This module includes an encounter with the leading edge of research and practice.

Assessment Methods

The format of resits will be determined by the Board of Examiners

Exams
Description Length Semester When Set Percentage Comment
Written Examination1202A40N/A
Other Assessment
Description Semester When Set Percentage Comment
Report2M30Up to 6 page report, including all figures on natural language processing
Report2M30Up to 6 page report, including all figures on large language models
Assessment Rationale And Relationship

The written examination assesses students’ understanding of the principles, methods, and behaviour of natural language processing, language modelling, and generative AI systems. The examination evaluates students’ ability to reason about language representations, model architectures, generative approaches, system limitations, evaluation methods, and ethical considerations associated with language-based AI systems. The examination assesses all module learning outcomes. (MLO1, MLO2, MLO3, MLO4)


The NLP coursework provides students with the opportunity to apply natural language processing techniques within a practical analytical setting. Students will analyse language or text data, implement and evaluate computational approaches, and communicate findings through a structured technical report. The assessment supports the development of practical skills in text processing, modelling, evaluation, and interpretation. (MLO1, MLO2, MLO3)


The LLM coursework assesses students’ ability to apply and critically evaluate large language models and generative AI approaches within practical contexts. Students will investigate the behaviour, performance, capabilities, and limitations of generative systems and communicate their analysis through a structured report supported by appropriate evidence and discussion. The assessment also supports critical reflection on ethical and societal considerations associated with generative AI systems. (MLO2, MLO3, MLO4)


The assessment structure supports the development of both conceptual understanding and applied technical skills, enabling students to evaluate, implement, and critically analyse language and generative AI systems within realistic computational contexts.


Alternative assessment:


For students with a Student Support Plan (SSP) who have alternative assessment as a reasonable adjustment and/or students with supported Personal Extenuating Circumstances (PEC), it may be necessary to set an alternative assessment as presented below. Due to the professional requirements of some programmes, alternative assessments may not be available even where students are eligible.


An oral examination comprising a 15-minute prepared topic followed by 15 minutes of questions from the overall module syllabus may be offered as an alternative to the written examination where appropriate. No known barriers to inclusion are anticipated within the coursework assessment structure, although alternative formats such as oral or recorded submissions may be considered where appropriate.

Reading Lists

Timetable