General provisions

The course is given within the Master's Programme in Language Technology and as a freestanding course.

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. Knowledge of English equivalent to what is required for entry to Swedish first-cycle courses and study programmes.

Learning outcomes

On completion of the course, to earn the grade Pass the student should at least 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 components of a statistical machine translation system;
4. build their own translation model using existing tools for statistical machine translation and evaluate and analyse the translation results;
5. describe other machine translation strategies, such as rule-based machine translation and neural machine translation, and clarify the differences between them and statistical machine translation;
6. implement components of machine translation systems or components used in evaluation or preprocessing.

Content

See the intended learning outcomes.

Instruction

The teaching consists of lectures and laboratory sessions under supervision.

Assessment

Examination takes place through oral and written presentation of assignments. The teacher can, as part of the examination require compulsory attendance and active participation in teaching modulees. Details about the examination are provided at the start of the course.