Statistical Natural Language Processing
Create a free account to unlock full content!
By registering, you agree to our Privacy Statement and Terms and Conditions.
Program Overview
Statistical Natural Language Processing (COMP0087)
Key Information
The module is part of the Faculty of Engineering Sciences, specifically the Computer Science department, and is worth 15 credits. Restrictions apply, with module delivery available for UG Masters (FHEQ Level 7) on MEng Computer Science and MEng Mathematical Computation, and for PGT (FHEQ Level 7) on various MSc programs including Artificial Intelligence for Biomedicine and Healthcare, Artificial Intelligence for Sustainable Development, Computational Statistics and Machine Learning, Data Science and Machine Learning, Machine Learning, and others.
Alternative Credit Options
There are no alternative credit options available for this module.
Description
Aims
The module introduces the basics of statistical natural language processing (NLP) and machine learning techniques relevant for NLP.
Intended Learning Outcomes
On successful completion of the module, a student will be able to understand relevant ML techniques, particularly in deep learning, and address the computational challenges involved in NLP.
Indicative Content
The module focuses on NLP applications and the machine learning techniques used to solve them, covering topics such as:
- Machine translation
- Sequence tagging
- Constituent and dependency parsing
- Information extraction
- Semantics
With a strong applied character, including coursework and lectures that mix practical aspects with theory and background, the module will also cover NLP tasks like:
- Language Models
- Machine Translation
- Text Classification
- Sequence Tagging
- Information Extraction
- Machine Reading Comprehension And NLP and ML methods such as:
- Encoder/Decoder Architectures
- Feature Engineering
- Deep Neural Networks
- RNNs, CNNs
- Attention
- Word Vectors
- Pretraining
Requisites
To be eligible, a student must:
- Be registered on a programme and year of study for which the module is formally available.
- Have an understanding of Basic Probability Theory, Linear Algebra, and Multivariate Calculus.
- Have proficiency in programming.
- Be able to install libraries on a computer.
- Have taken at least one introductory machine learning module.
Module Deliveries for 2026/27 Academic Year
Intended Teaching Term: Term 2, Postgraduate (FHEQ Level 7)
Teaching and Assessment
- Mode of study: In person
- Methods of assessment: 100% Group activity
- Mark scheme: Numeric Marks
Intended Teaching Term: Term 2, Undergraduate (FHEQ Level 7)
Teaching and Assessment
- Mode of study: In person
- Methods of assessment: 100% Group activity
- Mark scheme: Numeric Marks
Other Information
- Number of students on the module in the previous year: 145 (Postgraduate), 41 (Undergraduate)
- Module leader: Professor Pontus Saito Stenetorp