The course aims to familiarize students with recent research across a range of topics within NLP, mainly within the framework of neural network models, and with a focus on applications such as machine translation, summarisation, and semantic parsing. As an MSc-level course that assumes previous experience with NLP, it will discuss a range of different issues, including linguistic/representational capacity, computational efficiency, optimization, etc. There is no textbook for the course; readings will come from recent research literature.
1.1 This course explores current research on processing natural language: interpreting, generating, and translating
2.1 The course will focus mainly on deep learning approaches to various NLP tasks and applications. It will provide an introduction to the main neural network architectures used in NLP and how they are used for tasks such as syntactic and semantic parsing, as well as end-user applications such as machine translation and text summarization.
3.1 Building on linguistic and algorithmic knowledge taught in prerequisite courses, this course also aims to further develop students' understanding of the strengths and weaknesses of current approaches with respect to linguistic and computational considerations.
4.1 Practical assignments will provide the opportunity to implement and analyse some of the approaches considered.
By the end of the course, students should be able to do the following:
Curriculum explorer: Click here
SCQF Level: 11
Credits: 20