The schedule is preliminary and subject to change.

Last year’s materials are available for reference.

Week Day Plan
Week Day Plan
Week 1 Jan 15 Lecture Introduction

Resources
Jan 18 Lecture Neural Network Basics

Resources
Week 2 Jan 22 Lecture Probability, language models

Resources
Jan 25 Lecture Neural machine translation

Resources
Week 3 Jan 29 Lecture Evaluation of machine translation

Resources
Feb 01 Lecture Attention models

Resources
Week 4 Feb 05 Lecture Open-vocabulary translation

Resources
Feb 06 Lab Coursework set-up help. 15.10-16.00, room 4.12, Appleton Tower
Feb 07 Lab Coursework set-up help. 15.10-16.00, room 5.08, Appleton Tower
Feb 08 Lecture Morphology

Resources
Week 5 Feb 12 Lecture Learning from monolingual data

Resources
Feb 15 Lecture Advanced neural MT architectures

Resources
Flexible Learning Week No class.
Week 6 Feb 26 Lecture Learning from multilingual data

Resources
Mar 01 cancelled
Week 7 Mar 05 Lecture Phrase-based and syntax-based statistical MT

Resources
  • Lecture slides
  • Lecture slides (4up)
  • Koehn (2009). Statistical Machine Translation. Available electronically from the university library.
  • Williams, Sennrich, Post, Koehn (2016). Syntax-based Statistical Machine Translation.
Mar 08 Lecture Syntax

Resources
Week 8 Mar 12 Lecture Advanced Decoding Techniques

Resources
Mar 15 Coursework Coursework 1 due at 3pm
Lecture Tidbits and open challenges

Resources
Week 9 Mar 19 Lecture Wrap-up and exam discussion

Resources
Week 10 No class.
Week 11 No class.
Exam week Apr 30 exam in Appleton Tower Concourse (14:30-16:30)

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

Material on this page is freely reuasable under a Creative Commons attribution license,
and you are free to reuse it with appropriate credit. The website is based on source code by Adam Lopez, available on github.