Machine Learning for Linguists

After completing this course

• you know how to use the Python programming language and its libraries independently in order to solve natural language processing (NLP) tasks,
• you are familiar with the basic terminology of rule-based systems and machine learning methods and can describe their differences,
• you understand the difference between supervised and unsupervised learning and know how to apply these learning methods in some NLP tasks,
• you know how to use sequential models for parsing, for instance in part-of-speech tagging,
• you know how to use classifiers, such as decision trees, Naïve Bayes classifiers and neural networks,
• you know how to perform clustering on some language data,
• you know how to evaluate the performance of a machine learning system.

We use freely available material on the course (for instance, the NLTK Book: Steven Bird, Ewan Klein, and Edward Loper: Natural Language Processing with Python – Analyzing Text with the Natural Language Toolkit).

Additional material is distributed on the course.

This study unit is part of the elective common studies of the Master's Programme in Linguistic Diversity and Digital Humanities (LingDig). The study unit can also be taken as part of the elective studies of the Language Sciences study track of the Bachelor Programme in Languages. Additionally, the study unit is open to students of other study programmes and study tracks.

Second or third year of the bachelor studies or first year of master's studies.

The course comprises lectures, exercise sessions and independent work by the student.

As a general rule, attendance at the teaching sessions is not compulsory, but active participation is considered in the grading.

It is compulsory to participate in a possible final exam or other tests.

In addition to this course, the following courses are recommended: Mathematics for Linguistics, Building NLP Applications, Command Line Tools for Linguists and Statistical Methods for Linguists.  It is possible to acquire corresponding skills on other similar courses.

On this course, you will learn by doing assignments. Your learning is supported by lectures and exercise sessions. The assignments as well as other course material is distributed on an online learning platform (Moodle).

Your performance is graded on the scale 0–5.

The following criteria are considered in the grading:

• performance in the assignments and project work and timely completion of all tasks
• possibly performance in an exam or tests
  
• other activities and active participation in the course.
  

The course is taught in English.