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.
- 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
- Question 1
- Question 2
- Subquestion 1
2. Training Neural Networks
3. Training Neural Networks II
4. Convolutional Networks
5. Convolutional Networks II
6. Easter Monday
7. Object Detection & Segmentation, Neural Networks
8. Recurrent Neural Networks II, Word Embeddings
9. Recurrent Neural Networks III, Machine Translation
10. Deep Generative Models
11. Sequence Prediction, Reinforcement Learning
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.
All lecture materials for the years 2008—2017 are available in the course SVN:
For read-only access use username: student and password: student