96639 - Machine Translation

Learning outcomes

The student knows the history, theoretical principles and state-of-the-art developments of machine translation; s/he is able to devise, carry out, manage and evaluate complex machine translation projects involving several professionals and a variety of skills and competences, including those for pre- and post-editing in a variety of registers and sublanguages, in a way that is consistent with professional ethics; s/he is able to acquire higher-level knowledge and competences related to machine translation technology independently, and to employ them for the optimization of related language industry processes.

Course contents

In this course, the student will learn:

• the main phases of the history and evolution of machine translation
• the intuition behind the main principles underlying MT
• how to apply and interpret the most important evaluation metrics for machine-produced translations
• how to set up and maintain a MT model, including gathering and cleaning training data
• to use specialised MT software and utilities
  
• to think about MT systems critically and leverage their knowledge to boost productivity
  

Readings/Bibliography

Philipp Koehn (2020), "Neural Machine Translation", Cambridge University Press

Thierry Poibeau (2017), "Machine Translation", MIT Press

Joss Moorkens, S. Castilho, F. Gaspari, S. Doherty (2018), "Translation Quality Assessment: From Principles to Practice", Springer

Kyunghyun C., van Merrienboer B., Bahdanau D., Bengio Y. (2016) "On the Properties of Neural Machine Translation: Encoder-Decoder Approaches" arXiv.org > cs > arXiv:1409.1259

Teaching methods

Lectures and workshops

Assessment methods

Capstone project followed by a viva voce

Teaching tools

PowerPoint files used during lectures will be made available to students. Specific MT software will be used during workshops.

Office hours

See the website of Luca Astolfi