Course co-ordinator(s): Dr Ioannis Konstas (Edinburgh), Dr Alessandro Suglia (Edinburgh).
Aims:
This course aims to:
- lay the foundations of core concepts in Linguistics;
- present the most common Natural Language Processing (NLP) problems together with appropriate Machine Learning solutions;
- familiarise students with NLP applications in currently active research areas using Machine Learning techniques;
- enable students to build simple NLP applications using commonly used libraries;
- raise critical awareness of the appropriateness of NLP techniques and the relationships between them
Detailed Information
Course Description: Link to Official Course Descriptor.
Pre-requisites: none.
Location: Edinburgh.
Semester: 1.
Syllabus:
Linguistics Foundation - word classes, language models, syntax, semantics
NLP Problems - Part-of-speech tagging, language modelling, syntactic parsing, lexical semantics. Solutions to these problems will employ commonly-used machine learning algorithms, e.g., feature-based discriminative models, dynamic programming, word embeddings, and neural network architectures
NLP Applications - Popular NLP downstream tasks, such as Machine Translation, Machine Reading (Question Answering), and Dialogue Systems.
Learning Outcomes: Subject Mastery
- Critical understanding of core concepts in Linguistics.
- Detailed and integrated knowledge and understanding of common NLP problems, and the linguistic motivation behind them.
- Practical understanding of appropriate machine learning methodologies used to solve common NLP problems.
- Critical awareness of the appropriateness and performance of the different linguistic and machine learning techniques on NLP problems and applications, as well as the relationships between them.
- Use appropriate computer software to build NLP systems using machine learning.
- Present results in a way that demonstrates a deep understanding of the technical and broader issues of NLP.
Learning Outcomes: Personal Abilities
- Demonstrate the ability to learn independently, as well as deal with complex issues under time constraints.
- Critical analysis and substantial autonomy in selecting the correct solution to a given problem.
- Manage time, work to deadlines, and prioritise workloads.
Assessment Methods: Due to covid, assessment methods for Academic Year 2021-22 may vary from those noted on the official course descriptor. Please see the Computer Science Course Weightings and the Maths Course Weightings for 2020-21 Semester 1 assessment methods.
SCQF Level: 11.
Credits: 15.