Skip to content

Latest commit

 

History

History
 
 

week06_em

Generative Models, Expectation-Maximization and Word Alignment Models

Today's lecture will cover simple generative models, maximum likelihood estimation from both complete and incomplete data and latent variable word alignment models.

The Expectation-Maximization algorithm is a general algorithm for estimating models when some variables are not observed. It can be seen as a form of variational inference.

Videos:

  • our lecture and seminar (in english!)
  • alternative lecture on EM (outside NLP) Seminar will use this notebook.

Homework (due in class next week)

In preparation for next week's class on Machine Translation, you should form groups of five or six students, pick one of the following questions and be prepared to give a short presentation during the lecture.

Each person should read at least one paper and your group should probably meet in advance of the class to finalize your presentation.

As well as explaining the main ideas in the papers, please also pay attention to any problems with the experimental set up in the paper and comment on whether their conclusions are well supported by their results.

  1. What are the main computational and statistical bottlenecks in NMT? How can we reduce them?
  1. What are the pros/cons of different Encoder-Decoder architectures? (RNNs, ConvS2S, Transformer, etc.)
  1. How can monolingual data be used to improve NMT?
  1. How can we build NMT systems for language pairs with very little parallel data?
  1. Has NMT really bridged the gap between MT and human translation? What problems remain?