This is the 2017 syllabus. The 2018 syllabus will be substantially different in places, but you're welcome to refer to previous material here.

These slides are visual aids for the corresponding lectures, meant to guide you towards intuitons about the material. To really understand the material, you must read and interact with it in depth, which you cannot do by reading slides. I urge you to read the source material (especially the textbook) and not to rely extensively on the slides.

Date Topic Readings ( = optional)
Jan 11 Introduction
Jan 14 Probability and language models
  • Koehn, chapters 2 and 7
Jan 18 Latent variable models and word alignment
Jan 21 A brief tour of lexical translation models
Jan 25 Dynamic programming
Jan 28 Decoding
  • Koehn, chapter 6
Feb 01 Phrase-based translation
Feb 04 Measuring translation accuracy
Feb 08 Feature-based models
  • Koehn, chapter 9
Feb 11 Discriminative learning
Feb 22 Neural language models
Feb 25 Neural encoder-decoder models
Mar 01 Morphology
Mar 03 Modeling morphology in translation
Mar 07 Syntax
Mar 10 Synchronous context-free grammars
Mar 14 Modeling syntax and semantics with synchronous grammars
Mar 24 Decipherment
Mar 27 Exam review (optional)
Mar 31 The colorful history of machine translation (optional)

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.