Syllabus for Natural Language Processing

Decisions and guidelines

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

Learning outcomes

On completion of the course, to earn the grade Pass the student should at least be able to:

1. account for which products, services and technologies are typical for the field of language technology and at a general level account for the technology behind some important systems and account for the performance and commercial importance of these system;
2. account for important methodological considerations behind collection, selection and use of linguistic data in language technology;
3. apply and account for basic probability theory and principles of statistical inference on such data and apply principles of expectation-maximisation on models with hidden variables;
4. account for and apply statistical language models and different methods for regularisation;
5. implement simple statistical models of classification and annotation of symbol sequences particularly in system for morphological analysis and tagging of natural language, and evaluate such systems;
6. account for and implement algorithms for syntactic parsing and disambiguation and adapt and evaluate such systems for selected languages;
7. account for and implement language technology methods that capture and/or classify the contents of natural language text, and account for how such systems can be evaluated;
8. present the results of these kinds of language technology tasks in a professionally adequate way both orally and in writing.

Instruction

The teaching is given as lectures and laboratory sessions under supervision.

Assessment

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