Statistical Machine Translation

Date	Topic	Readings (starred=graduate level)
Jan 26	(snow day)
Jan 28	Introduction	Koehn, Chapter 1.2 Weaver (1949), Translation Kay, Translation
Feb 02	Basics in Language and Probability	Koehn, Chapter 2.1 and 3
Feb 04	Language Models	Koehn, Chapter 7
Feb 09	IBM Model 1 and the EM Algorithm	Koehn, Chapter 4.1-4.2 Knight (1997), Automating Knowledge Acquisition for Machine Translation
Feb 11	Advanced Alignment Models	Koehn, Chapter 4.4 Dyer et al. (2013), A Simple, Fast, and Effective Reparameterization of IBM Model 2 Vogel et al. (1996), HMM-Based Word Alignment in Statistical Translation
Feb 16	Phrase-Based Models	Koehn, Chapter 5 Durrani et al. (2013), Can Markov Models Over Minimal Translation Units Help Phrase-Based SMT?
Feb 18	Decoding (Demo)	Koehn, Chapter 6 Heafield et al. (2014), Faster Phrase-Based Decoding by Refining Feature State
Feb 23	Evaluation	Koehn, Chapter 8 Graham et al. (2014), Is Machine Translation Getting Better over Time?
Feb 25	Tuning	Koehn, Chapter 9.1-9.3
Mar 01	Sparse Features	Koehn, Chapter 9.4 Chiang (2012), Hope and Fear for Discriminative Training of Statistical Translation Models Cherry and Foster (2012), Batch Tuning Strategies for Statistical Machine Translation Hopkins and May (2011), Tuning as Ranking Wuebker et al. (2012), Leave-One-Out Phrase Model Training for Large-Scale Deployment Yu et al. (2013), Max-Violation Perceptron and Forced Decoding for Scalable MT Training
Mar 03	Introduction to Moses
Mar 08	Corpus Acquisition from the Internet	Uszkoreit et al. (2010), Large Scale Parallel Document Mining for Machine Translation Resnik and Smith (2003), The Web as a Parallel Corpus Buck and Heafield (2014), N-gram Counts and Language Models from the Common Crawl
Mar 10	(no class)
Mar 22	Reordering	Koehn, Chapter 10.3 Genzel (2010), Automatically Learning Source-side Reordering Rules for Large Scale Machine Translation Bisazza and Federico (2010), Chunk-based Verb Reordering in VSO Sentences for Arabic-English Statistical Machine Translation
Mar 24	Morphology	Koehn, Chapter 10.2 Stymne et al. (2013), Generation of Compound Words in Statistical Machine Translation into Compounding Languages Fraser et al. (2012), Modeling Inflection and Word-Formation in SMT Chahuneau et al. (2013), Translating into Morphologically Rich Languages with Synthetic Phrases
Mar 29	Syntax-Based Models	Koehn, Chapter 11.1-11.2
Mar 31	Syntax-Based Decoding I	Koehn, Chapter 11.3
Apr 05	Syntax-Based Decoding II	Koehn, Chapter 11.3 Hopkins and Langmead (2010), SCFG Decoding Without Binarization Sennrich (2014), A CYK+ Variant for SCFG Decoding Without a Dot Chart
Apr 07	Semantics	Cook et al. (2011), The World Color Survey Database - History and Use Banarescu et al. (2013), Abstract Meaning Representation for Sembanking
Apr 12	Introduction to Neural Networks	Koehn (2016), Neural Network Chapter Makin (2006), Backpropagation Tensorflow, Neural network online demo
Apr 14	Neural Language Models	Bengio et al. (2002), A Neural Probabilistic Language Model Tomas Mikolov, Statistical Language Models Based on Neural Networks, Chapter 3
Apr 19	Neural Translation Models	Zhang et al. (2014), Bilingually-constrained Phrase Embeddings for Machine Translation Devlin et al. (2014), Fast and Robust Neural Network Joint Models for Statistical Machine Translation Bahdanau et al. (2015), Neural Machine Translation by Jointly Learning to Align and Translate
Apr 21	Training Neural Networks	LeCun et al. (1998), Efficient BackProp Srivastava et al. (2014), Dropout - A Simple Way to Prevent Neural Networks from Overfitting
Apr 26	Computer Aided Translation	Barrachina et al. (2009), Statistical Approaches to Computer-Assisted Translation Germann (2014), Dynamic Phrase Tables for Machine Translation in an Interactive Post-editing Scenario