Natural Language Understanding (2016-17)

Course Overview

This course covers advanced methods in natural language understanding. At its core are methods for learning linguistic representations, at all levels of analysis: lexicon, syntax, semantics, and discourse.

The focus of the course will be on deep learning methods for learning linguistic representations, but standard discriminative and unsupervised methods will also be introduced. We will cover word embeddings, feed-forward neural networks, recurrent neural networks, recursive neural networks, and convolutional neural networks. In addition to the relevant architectures and learning algorithms, we will introduce deep learning approaches to a range of natural language understanding tasks, including language modeling, part-of-speech tagging, parsing, question answering, semantic role labeling, semantic composition, sentiment analysis, and discourse coherence.

Mailing List and Discussion Forum

Announcements regarding the course will be posted to the course mailing list. All students taking the course are automatically subscribed to this list. Previous postings can be accessed using the mailing list archive.

The course uses a Piazza discussion forum for questions relating to the course material or the assignments. If you are enrolled in the course, you should have received an invitation to join Piazza in week 2. Contact the lecturers if you haven't.

Virtual Learning Environment

The course will use Blackboard Learn for various activities. In particular the quizzes, assignments, and lecture recordings can be found there. If you are enrolled in the course, you will automatically have access to the Learn page of the course. Materials that are not Learn are on this web site.

Home : Teaching : Courses 

Informatics Forum, 10 Crichton Street, Edinburgh, EH8 9AB, Scotland, UK
Tel: +44 131 651 5661, Fax: +44 131 651 1426, E-mail:
Please contact our webadmin with any comments or corrections. Logging and Cookies
Unless explicitly stated otherwise, all material is copyright © The University of Edinburgh