NPFL087 — Statistical Machine Translation

The course covers the area of machine translation (MT) in its current breadth, delving deep enough in each approach to let you confuse every existing MT system. We put a balanced emphasis on several imporant types of state-of-the-art systems: phrase-based MT, surface-syntactic MT and (a typically Praguian) deep-syntactic MT. We do not forget common pre-requisities and surrounding fields: extracting translation equivalents from parallel texts (including word alignment techniques), MT evaluation or methods of system combination.

We aim to provide a unifying view of machine translation as statistical search in a large search space, well supported with practical experience during your project work in a team or alone. Finally, we also attempt to give a gist of emerging approaches in MT, such as neural networks.

About

SIS code: NPFL087
Semester: summer
E-credits: 6
Examination: 2/2 C+Ex
Instructor: Ondřej Bojar


Lectures

1. Introduction to Deep Learning Slides Video Questions

2. Training Neural Networks Slides Video

3. Training Neural Networks II Slides Video

4. Convolutional Networks Slides Video

5. Convolutional Networks II Slides Video

6. Easter Monday

7. Object Detection & Segmentation, Neural Networks Slides Video

8. Recurrent Neural Networks II, Word Embeddings Slides Video

9. Recurrent Neural Networks III, Machine Translation Slides Video

10. Deep Generative Models Slides Video

11. Sequence Prediction, Reinforcement Learning Slides Video

12. Sequence Prediction II, Reinforcement Learning II Slides

13. Practical Methodology, TF Development, Advanced Architectures Slides


Requirements

Key requirements:

  • Work on a project (alone or in a group of two to three).
  • Present project results (~30-minute talk).
  • Write a report (~4-page scientific paper).

Contributions to the grade:

  • 10% three MTtalks CodEx exercises,
  • 30% written exam,
  • 50% project report,
  • 10% project presentation.

Final Grade: ≥50% good, ≥70% very good, ≥90% excellent.

1. Introduction to Deep Learning

 Feb 26 Slides Video Questions

  1. Question 1
  2. Question 2
    1. Subquestion 1

2. Training Neural Networks

 Mar 05 Slides Video

3. Training Neural Networks II

 Mar 12 Slides Video

4. Convolutional Networks

 Mar 19 Slides Video

5. Convolutional Networks II

 Mar 26 Slides Video

6. Easter Monday

 Apr 02

7. Object Detection & Segmentation, Neural Networks

 Apr 09 Slides Video

8. Recurrent Neural Networks II, Word Embeddings

 Apr 16 Slides Video

9. Recurrent Neural Networks III, Machine Translation

 Apr 23 Slides Video

10. Deep Generative Models

 Apr 30 Slides Video

11. Sequence Prediction, Reinforcement Learning

 May 07 Slides Video

12. Sequence Prediction II, Reinforcement Learning II

 Mar 19 Slides

13. Practical Methodology, TF Development, Advanced Architectures

 May 21 Slides

The exam is written and consists of 7 question, each equally important.

Archive

All lecture materials for the years 2008—2017 are available in the course SVN:

https://svn.ms.mff.cuni.cz/projects/NPFL087
For read-only access use username: student and password: student