Skip to main content

Natural Language Processing Applications

Overview

  • Credit value: 30 credits at Level 6
  • Convenor: Dr Paul Nulty
  • Assessment: a mini-project (40%) and two-hour open book examination (60%)

Module description

In this module we explore the intersection of computational techniques and human language. You will learn to analyse and interpret text data using state-of-the-art natural language processing (NLP) tools and methods. This module prepares you for advanced roles in AI and data science, emphasising practical skills and applications.

Indicative syllabus

  • Introduction to NLP
  • Text pre-processing
  • Language models
  • Post-training methods for language models
  • Part-of-speech tagging
  • Named entity recognition
  • Syntax and parsing
  • Distributional semantics
  • Sentiment analysis
  • Topic modelling
  • Machine translation
  • Text classification
  • Information retrieval
  • Text summarisation
  • Speech recognition and synthesis
  • Ethics in NLP

Learning objectives

By the end of this module you will be able to:

  • demonstrate an understanding of the fundamental concepts and techniques in NLP
  • apply various NLP algorithms and models to analyse and interpret text data
  • evaluate the performance of different NLP models and techniques in various applications
  • understand the ethical considerations and potential biases in NLP applications
  • analyse complex text data and develop solutions using NLP techniques
  • critically evaluate the effectiveness of different NLP approaches in solving real-world problems
  • formulate and test hypotheses related to language data and NLP models
  • synthesise knowledge from mathematics, computer science, psychology and linguistics to address NLP challenges
  • implement NLP algorithms using programming languages such as Python
  • use specialised NLP libraries and tools to process and analyse text data
  • develop and deploy NLP applications for tasks such as sentiment analysis, machine translation and information retrieval
  • conduct experiments and analyse results to improve NLP models
  • deploy and tune language models for generative and creative applications
  • communicate complex technical concepts and findings effectively to both technical and non-technical audiences
  • work independently and collaboratively on NLP projects, demonstrating strong teamwork and project management skills
  • demonstrate an increased awareness of ethical practices and the social impact of NLP technologies.