Natural Language Processing (NLPG-H) - COM00069H

«Back to module search

Module summary

The NLPG module provides the foundational knowledge and skills required to understand and work with Natural Language Processing (NLP) systems. Students will explore the core concepts, methods, and challenges involved in enabling machines to process, understand, and generate human language. Topics taught include text preprocessing, tokenisation, syntax and semantics, word embeddings, language modelling, sequence labelling, and basic neural architectures for NLP. The module also contrasts classical approaches leading up to Transformer Models. It introduces key frameworks, evaluation metrics and datasets commonly used in NLP research and development. Through practical exercises and projects, students will build and evaluate simple NLP pipelines and models, developing an appreciation for how these foundations scale into modern LLMs. This grounding prepares students to engage critically with the technical and linguistic aspects of Natural Language technologies and to appreciate and address the ethical considerations that arise from them.

Module will run

Occurrence	Teaching period
A	Semester 1 2026-27

Module aims

The NLPG module aims to give students a grounding in basic concepts and skills relating to Natural Language Processing.

In addition to introducing key foundational concepts, methods and challenges, the module seeks to enable students to differentiate between classical NLP approaches and a variety of modern neural architectures, and to implement core NLP techniques to build simple NLP pipelines and models.

Students will develop practical skills in construction and evaluation of basic NLP models, and will engage critically with the technical, linguistic and ethical challenges posed by the development and deployment of the technologies in real-world applications.

Module learning outcomes

• Explain key concepts and techniques in natural language processing, including tokenisation, part-of-speech tagging, parsing, and semantic analysis.

• Construct basic NLP pipelines for tasks such as text classification, named entity recognition, and sentiment analysis.

• Apply foundational methods such as word embeddings, n-gram models, and recurrent neural networks to represent and model language.

• Evaluate NLP models using standard metrics and datasets, demonstrating an understanding of model performance and limitations.

• Describe how classical and neural approaches to NLP underpin the development of modern Large Language Models.

Indicative assessment

Task	% of module mark
Essay/coursework	100.0

Special assessment rules

None

Indicative reassessment

Task	% of module mark
Essay/coursework	100.0

Module feedback

Feedback is provided through work in practical sessions, and after the final assessment as per normal University guidelines.

Indicative reading

TBC