Entry requirements

A Bachelor's degree and (1) 60 credits in language technology/computational linguistics, or (2) 60 credits in computer science, or (3) 60 credits in a language subject, 7.5 credits in computer programming and 7.5 credits in logic/discrete mathematics. Also required is 7.5 credits in machine learning, and proficiency in English equivalent to the general entry requirements for first-cycle (Bachelor's level) studies.

Learning outcomes

For the grade Pass, after completing the course the student should be able to

1. explain, apply, and assess manual and automatic evaluation methods for machine translation
2. analyse and critically review scientific publications in the field of machine translation
3. describe and critically discuss the architecture of machine translation systems and evaluation of machine translation systems
4. build their own translation model using existing tools for machine translation and evaluate and analyse the translation results
5. compare different types of machine translation strategies, such as rule-based, statistical, and neural machine translation
6. plan and carry out research tasks based on sound methodological principles and within the given time limits.

Content

The course provides an overview of different types of machine translation systems with a focus on architecture, usage and evaluation.

Instruction

The teaching consists of lectures and laboratory sessions under supervision.

Assessment

Examination takes place through oral and written presentation of assignments. The subtasks of the examination are announced in writing by the course coordinator at the start of the course.

If there are special reasons for doing so, an examiner may make an exception from the method of assessment indicated and allow a student to be assessed by another method. An example of special reasons might be a certificate regarding special pedagogical support from the University's disability coordinator.