Instructor: Dr. Yoav Goldberg
Email: yogo / cs.biu.ac.il
Office: Room 4 building 216
Office Hours: By appointment
This course aims to explain modern statistical machine translation systems, how they work, what doesn't work, and where we are likely to improve.
There will be 3 assignment. The assignments are 40% of the grade, and the final exam is 60%. Students who wish to do so may take on a course project as 30% of the grade, making the exam weigh only 30%.
The course is self contained, but references to extra reading materials will be provided.
Assignment 1 -- Evaluation. Deadline: April 18, 2016
Assignment 2 -- Alignment. Deadline: May 15, 2016
Assignment 3 -- Decoding. Deadline: June 22, 2016
Here is a nice exercise, developed by Kevin Knight and put into this form by Adam Lopez. Please try to work on it before next class. It's fun! (no grade attached)
Introduction, noisy channel, parallel corpora. slides
Reading Classic Intro to Modern MT
Language models, Evaluation. slides
o Reading Smoothing details || Large LMs / Stupid Backoff || BLEU
o Examples of generating sentences from twitter based unigram, bigram and trigram models.
Word-word translations (Alignments, IBM model 1, EM). Slides More slides
o Reading Model 1 and 2 introduced by Mike Collins || IBM models introduced by Kevin Knight
More Alignments (Models 2,3, HMM-alignment, Alignment Eval, Available Software). Slides
o Reading Simple but Effective Improvements to Model 1 || Description and Comparison of Various Models, Evaluation, Symmetrization || Improved HMM Alignment
o Software Giza++ (Models 1-5, HMM) || Berkeley Aligner (HMM+) || Nile (Supervised)
Phrase-based translation 1 (using alignments, phrase table extraction). Slides More slides
Phrase-based translation 2 (decoding). Slides More sldes
o Reading A formal description of phrase-based stack decoding || Phrase-based translation paper
o Software Moses (phrase-based decoder)
Reoredering Slides
Syntax Based Translation 1 (Hiero) Slides More Slides
o Reading The Hiero Translation Model
Syntax Based Translation 2 (GHKM Rules) Slides More Slides
o Reading GHKM rules definition
o Demo GHKM rules extraction demo
Syntax Based Translation 3 (GHKM Decoding -- Tree to String and String to Tree) Slides More Slides
Neural MT
o Reading Lecture notes by Cho
(Chapters 5 and 6)
Recent Advances in Neural MT
o Diverse n-best lists (Cho)
o Sub-word Units (Sennrich et al)
o Linguistic Features (Sennrich et al)
o Monolingual Language Model
(Sennrich et al)