Courses and Tutorials on DSM

Course materials – ESSLLI 2009 – NAACL-HLT 2010 – ESSLLI '16 & '18 – ESSLLI '21 & '22 – U Fribourg 2026/27 – Software & data sets – Bibliography

This page contains the most up-to-date version of the course slides, example scripts, and exercises. Previous instantiations of the course (e.g. at ESSLLI summer schools) may have used older versions of the slides, focused on specific topics, or contained additional specialised material not included in the master version.

All teaching materials are made available under a CC-by-sa license and can be obtained from the wordspace repository on R-Forge.
There are currently issues with access to R-Forge being blocked due to repeated cyber attacks. If these continue, the wordspace repository will be migrated to GitHub or another software development platform.

presentation slides (PDF, 2.2 MB) – handout (PDF, 2.1 MB) – R code: hands_on_part1.R

• motivation and geometric intuition
• distributional vs. semantic similarity
• practice: software setup, first steps with the wordspace package

presentation slides (PDF, 1.3 MB) – handout (PDF, 1.0 MB) – R code: hands_on_part2.R – load your own data: hands_on_part2_input_formats.R

• formal definition of a DSM, taxonomy of parameters
• collecting co-occurrence data: what counts as a context?
• mathematical operations on DSM vectors
• computing distances/similarities
• hands-on: building DSMs and exploring different parameter settings

• Software & data sets
• Bibliography & links