MT | 2017 Syllabus

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

Week	Day	Plan
Week	Day	Plan
Week 1	Jan 16	Lecture Introduction Resources Piazza signup Lecture recording Automating knowledge acquition for machine translation (Knight) Basic probability theory (Goldwater) 1A. Why probability? (video lecture) 1B. Brief review of probability (video lecture) 1C. n-gram language models (video lecture) Note on n-gram language models Language Modeling (Collins) Koehn, chapters 1--3
Week 1	Jan 19	Lecture Probability, language models, and conditional language models Resources Lecture recording Note on word alignment and the expectation maximization algorithm The expectation maximization algorithm: a short tutorial A tutorial MT workbook (Knight) Koehn, Chapter 4
Week 2		No in-person lectures in week 2 Resources Advanced translation models (video lecture) Decoding (video lecture) Koehn, chapter 6
Week 2	Jan 24	Lab Latent-variable translation models Resources Lab materials
Week 3	Jan 30	Lecture Phrase-based translation and decoding Resources Lecture recording Statistical phrase-based translation (Koehn et al.) The complexity of phrase alignment problems (DeNero and Klein)
Week 3	Feb 02	Lecture Evaluation of translation systems Resources Lecture recording (no sound) Models of translation competitions (Hopkins and May) Ten Years of WMT Evaluation Campaigns: Lessons Learnt (Bojar et al.)
Week 4	Feb 06	Lecture Words and Morphology Resources Lecture recording Bender, chapters 2–4
Week 4	Feb 09	Coursework Coursework 1 due at 4pm Lecture Morphology (continued); maximum entropy models Resources Lecture recording
Week 5	Feb 13	Lecture Neural probabilistic language models Resources Lecture recording A neural probabilistic language model (Bengio et al.)
	Feb 14	Lab Neural probabilistic language models Resources Lab materials
	Feb 16	Lecture Conditional neural language models Resources Lecture recording Neural machine translation by jointly learning to align and translate (Bahdanau et al.)
		No class the week of Feb 20
Week 6	Feb 27	Lecture Large vocabulary language modeling Resources Lecture recording Pragmatic neural language modelling in machine translation (Baltescu and Blunsom) Strategies for training large vocabulary neural language models (Chen et al.) Finding function in form: Compositional character models for open vocabulary word representation (Ling et al.)
Week 6	Mar 02	Lecture Large vocabulary translation modeling Resources Lecture recording On Using Very Large Target Vocabulary for Neural Machine Translation (Jean et al.) Addressing the Rare Word Problem in Neural Machine Translation (Luong et al.) Neural Machine Translation of Rare Words with Subword Units (Sennrich et al.) Google's Neural Machine Translation System (Wu et al.) Character-based Neural Machine Translation (Ling et al.) Fully Character-Level Neural Machine Translation without Explicit Segmentation (Lee et al.)
Week 7	Mar 06	Lecture Attention Resources Lecture recording Effective Approaches to Attention-based Neural Machine Translation (Luong et al.) Incorporating Structural Alignment Biases into an Attentional Neural Translation Model (Cohn et al.) [NEW!] Neural Machine Translation and Sequence-to-sequence Models: A Tutorial
	Mar 07	Lab Coursework 2 support
	Mar 09	Lecture Using monolingual data in NMT Resources Lecture recording On using monolingual corpora in neural machine translation (Gulcehre et al.) Improving Neural Machine Translation Models with Monolingual Data (Sennrich et al.) Generalizing and Hybridizing Count-based and Neural Language Models (Neubig and Dyer) Incorporating Discrete Translation Lexicons into Neural Machine Translation (Arthur et al.)
Week 8	Mar 13	Coursework Coursework 2 due at 4pm Lecture Multi-source and zero-shot translation Resources Lecture recording Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism (Firat et al.) Zero-Resource Translation with Multi-Lingual Neural Machine Translation (Firat et al.) Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation (Johnson et al.)
Week 8	Mar 16	Lecture Syntax and translation Resources Lecture recording Bender, chapters 5--8 Phrasal cohesion and statistical machine translation (Fox)
Week 9	Mar 20	Lecture Recurrent neural network grammars Resources Lecture recording Recurrent neural network grammars (Dyer et al.) What Do Recurrent Neural Network Grammars Learn About Syntax? (Kuncoro et al.) Learning to parse and translate improves neural machine translation (Eriguchi et al.)
Week 9	Mar 23	Lecture Minimum risk training and evaluation revisited Resources Lecture recording Minimum Risk Training for Neural Machine Translation (Shen et al.) How grammatical is character-level neural machine translation? Assessing MT quality with contrastive translation pairs (Sennrich)
Week 10	Mar 27	Lecture Decipherment Resources Lecture recording Large scale decipherment for out-of-domain machine translation (Dou and Knight) The Copiale Cipher (Knight et al.) What we know about the Voynich manuscript (Reddy and Knight)
	Mar 28	Lab Coursework 3 support
	Mar 30	Lecture History (final lecture) Resources Lecture recording The dawn of statistical ASR and MT (Jelinek) Fred Jelinek (Liberman) Oh yes, everything's right on schedule, Fred (Brown and Mercer) The Great A.I. Awakening (Lewis-Kraus, NY Times Magazine)
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. The website is based on source code by Adam Lopez, available on github.

Machine translation