Module overview
This module gives students an introduction to natural language processing (NLP) algorithms and an understanding of how to implement NLP applications.
Linked modules
COMP3222 or COMP3223
Aims and Objectives
Learning Outcomes
Subject Specific Intellectual and Research Skills
Having successfully completed this module you will be able to:
- Be able to describe and discuss the different subareas of NLP
- Understand the potential and limitations of NLP techniques within application areas
Subject Specific Practical Skills
Having successfully completed this module you will be able to:
- Be able to implement NLP algorithms and techniques
- Be able to process text corpora ready for application of NLP algorithms and techniques
Knowledge and Understanding
Having successfully completed this module, you will be able to demonstrate knowledge and understanding of:
- The underlying algorithmic and linguistic basis for NLP techniques
- Algorithms commonly used for NLP problems such as information extraction, machine translation, text summarization and question answering
- Key concepts, tools and approaches for handling textual data
Syllabus
Working with Text Corpora
- Text Normalization
- Regular Expressions
- Evaluation Metrics and Linguistic Resources
Vector Semantics and Embeddings
- Lexical and Vector Semantics
- TF-IDF
- Word2Vec
Language Modelling and Parts of Speech Tagging
- Language Modelling
- Parts of Speech Tagging
Syntactic and Semantic Parsing
- Syntactic parsing
- Text Chunking
- Dependency Parsing
- Word Senses and WordNet
Sequence Processing with Recurrent Neural Networks
- Recurrent Neural Networks
- Sequence Processing for NLP Applications
- Managing Context using LSTM’s and GRU’s
Large Language Models
- Masked Language Models
- Prompting and Instruction Tuning
Information Extraction
- Named Entity Recognition
- Relation Extraction
- Temporal, Event and Location Extraction
Applications of NLP (example topics below)
- Statistical Machine Translation
- Semantic Role Labelling
- Question Answering
Learning and Teaching
Teaching and learning methods
Lectures and formative laboratories.
Type | Hours |
---|---|
Lecture | 24 |
Preparation for scheduled sessions | 18 |
Specialist Laboratory | 8 |
Wider reading or practice | 90 |
Revision | 10 |
Total study time | 150 |
Resources & Reading list
Internet Resources
Speech and Language Processing, 3rd ed. draft (online preferred).
Textbooks
Aurelien Geron (2017). Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems. O′Reilly.
S.Bird, E.Klein & E.Loper (2009). Natural Language Processing with Python. O'Reilly.
Jurafsky and Martin (2009). Speech and Language Processing. Prentice Hall.
Assessment
Summative
This is how we’ll formally assess what you have learned in this module.
Method | Percentage contribution |
---|---|
Examination | 100% |
Referral
This is how we’ll assess you if you don’t meet the criteria to pass this module.
Method | Percentage contribution |
---|---|
Examination | 100% |
Repeat
An internal repeat is where you take all of your modules again, including any you passed. An external repeat is where you only re-take the modules you failed.
Method | Percentage contribution |
---|---|
Examination | 100% |
Repeat Information
Repeat type: Internal & External