Machine Learning in Natural Language Processing
Syllabus, Master's level, 5LN708
- Code
- 5LN708
- Education cycle
- Second cycle
- Main field(s) of study and in-depth level
- Language Technology A1F
- Grading system
- Fail (U), Pass (G), Pass with distinction (VG)
- Finalised by
- The Department Board, 1 September 2023
- Responsible department
- Department of Linguistics and Philology
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
In order to pass the course, a student must be able to
- discuss basic aspects of machine learning applied to natural language data
- apply probability theory and statistic inference on linguistic data
- use standard software packages for machine learning
- implement models for classification and structured prediction
- design neural networks using any standard library.
In all cases, with a certain degree of independent creativity, clearly state and critically discuss methodological assumptions, apply state-of-the-art methods for evaluation, and present the result in a professionally adequate manner.
Content
The course contains basic concepts in machine learning with a special focus on language technology. The course has a theoretical part where mathematical modeling and optimization are studied more generally, and a more applied part focusing on language models.
Instruction
The teaching is given as lectures, seminars and laboratory sessions under supervision.
Assessment
The course is examined through assignments. The teacher can require compulsory attendance and active participation in seminars as part of the examination.
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.