Machine Learning (Level 2)
Purpose
The purpose of this course is to give a solid methodological
foundation in machine learning for language technology,
an overview of the most widely used approaches to learning,
and an in-depth understanding of a subset of these approaches.
Contents
The course consists of three parts:
- The first part of the course (taught in the first intensive week)
gives a general introduction to machine learning, covering basic
methodological principles and introducing the major learning paradigms
used in language technology, such as the following:
- Decision trees
- Artificial neural networks
- Statistical learning methods
- Memory-based learning
- Transformation-based learning
- Inductive logic programming
- The second part of the course (taught in the first and second intensive
week) consists of two or three advanced tutorials on specific learning
methods, taught by experts in the respective fields. The final selection of
methods will be determined on the basis of the participants' interest, but
strong candidates are memory-based learning, transformation-based learning
and inductive logic programming.
- The third part of the course is a practical project (reported at the
closing seminar) applying one or more of the learning methods covered in the
course to one or more areas of language technology.
Prerequisites
At least one of the courses Natural Language Processing (Level 1) and
Speech Technology (Level 1) or the equivalent. Some knowledge of programming
and basic concepts of statistics is useful but not absolutely necessary.