The course belongs to the MA Programme Linguistic Diversity in the Digital Age.

• study track: language technology
• modules: Studies in Language Technology (LDA-T3100), Essentials in Language Technology (LDA-TA500), Comprehensive specialization in Language Technology (LDA-TB500)

This is an optional course.

The course is available to students from other study tracks and degree programmes.

After successfully completing the course, students will be able to:

• describe the differences between various machine translation paradigms (rule-based, statistical, neural machine translation)
• explain the basics of neural machine translation and the most common model architectures
• describe the issues related to machine translation evaluation
• train, test and evaluate a neural machine translation system including the appropriate pre- and post-processing steps
• read, understand and present scientific papers on current challenges in machine translation.

Students can take this course in year 1 or 2. The course is offered during the spring term in period 4.

• History of machine translation and paradigms
• Parallel corpora, alignment, preprocessing
• Human and automatic evaluation of machine translation
• Introduction to neural networks and neural machine translation
• Common model architectures: sequence-to-sequence models, attention, self-attention
• Open vocabulary translation
• Current topics in machine translation: multilingual MT, unsupervised MT, multimodal MT, domain adaptation, etc.

• Weekly lectures and hands-on assignments
• Shared-task-based assignment with report
• Seminar presentation on current topic

• Philipp Koehn (2012): Statistical machine translation. Cambridge. [Including appendix chapter on neural machine translation]
• Mikel Forcada (2017): Making sense of neural machine translation. In: Translation Spaces 6/2.
• Additional material distributed in the course.

Grading follows the standard scale 0 – 5. The following aspects are taken into account in grading:

• Hands-on assignments (⅓)
• Shared-task-based assignment with report (⅓)
• Seminar presentation on current topic (⅓)

Prerequisites:

• Command-line course or equivalent

Recommended optional studies:

• Programming for linguists or equivalent (BA level)
• Mathematics for linguists or equivalent (BA level)
• Machine learning for linguists or equivalent (BA level)