Courses

Natural Language Processing II
2015-present (offered in Spring)

I’m organising Natural Language Processing II at UvA (the course is focused on machine translation). This is the third edition which I organise, the first one was in the spring of 2015.

The course is organised in three blocks

  • Unsupervised word alignments: directed models (EM estimation and VB) and undirected models (MLE via gradient-based optimisation)
  • Statistical machine translation: (hierarchical) phrase-based MT (linear models), latent-variable CRF for hierarhical PBSMT
  • Neural machine translation: fully supervised sequence to sequence models, deep generative models

Bayesian inference for PCFGs
March 2017 - 6EC

4 weeks course on Bayesian inference for PCFGs, here is a list of the topics covered:

My student Daan van Stigt did an excellent job! Check his amazing notebooks.


Parsing as deduction and Monte Carlo sampling for PCFGs
June 2015 - 6EC

4 weeks course on MC techniques for PCFGs, here is a list of the topics covered:


Projects

Featurised EM

In the spring of 2016, I offered a BA project on feature-rich unsupervised alignment models. My student Guido Linders did a great job (thesis, code)!

Slice sampling from PCFGs

In the spring of 2015, I offered a BA project on slice sampling from PCFGs. My student Iason de Bondt did a great job (thesis, code)!