Lecture materials will be posted after each lecture.

The course is being updated, but Last year’s materials are available for reference.

Week Day Plan
Week Day Plan
Week 1 Jan 16 Lecture Introduction

Resources
Jan 19 Lecture Probability, language models, and conditional language models

Resources
Week 2 No in-person lectures in week 2

Resources
Jan 24 Lab Latent-variable translation models

Resources
Week 3 Jan 30 Lecture Phrase-based translation and decoding

Resources
Feb 02 Lecture Evaluation of translation systems

Resources
Week 4 Feb 06 Lecture Words and Morphology

Resources
Feb 09 Coursework Coursework 1 due at 4pm
Lecture Morphology (continued); maximum entropy models

Resources
Week 5 Feb 13 Lecture Neural probabilistic language models

Resources
Feb 14 Lab Neural probabilistic language models

Resources
Feb 16 Lecture Conditional neural language models

Resources
No class the week of Feb 20
Week 6 Feb 27 Lecture Large vocabulary language modeling

Resources
Mar 02 Lecture Large vocabulary translation modeling

Resources
Week 7 Mar 06 Lecture Attention

Resources
Mar 07 Lab Coursework 2 support
Mar 09 Lecture Using monolingual data in NMT

Resources
Week 8 Mar 13 Coursework Coursework 2 due at 4pm
Lecture Multi-source and zero-shot translation

Resources
Mar 16 Lecture Syntax and translation

Resources
Week 9 Mar 20 Lecture Recurrent neural network grammars

Resources
Mar 23 Lecture Minimum risk training and evaluation revisited

Resources
Week 10 Mar 27 Lecture Decipherment

Resources
Mar 28 Lab Coursework 3 support
Mar 30 Lecture History (final lecture)

Resources
Week 11 No lectures or labs. Work on final coursework.
Week 12 Apr 13 Coursework Coursework 3 due at 4pm

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. You can get the source code on github.