Differences
This shows you the differences between two versions of the page.
| Both sides previous revisionPrevious revisionNext revision | Previous revision | ||
| course:slides [2026/09/30 22:17] – schtepf | course:slides [2026/10/05 12:28] (current) – [Part 1: Introduction] schtepf | ||
|---|---|---|---|
| Line 23: | Line 23: | ||
| [[http:// | [[http:// | ||
| + | * from collocations to distributional semantics | ||
| * motivation and geometric intuition | * motivation and geometric intuition | ||
| * distributional vs. semantic similarity | * distributional vs. semantic similarity | ||
| - | * practice: //software setup, first steps with the '' | + | * hands-on: //software setup, first steps with the '' |
| ==== Part 2: The parameters of a DSM ==== | ==== Part 2: The parameters of a DSM ==== | ||
| Line 35: | Line 36: | ||
| * mathematical operations on DSM vectors | * mathematical operations on DSM vectors | ||
| * computing distances/ | * computing distances/ | ||
| - | * practice: //building DSMs and exploring different parameter settings// | + | * hands-on: //building DSMs and exploring different parameter settings// + //how to load your own data and create a DSM// |
| - | ==== Part 3 ==== | + | ==== Part 3: Evaluation of DSM similarity |
| + | [[http:// | ||
| - | ==== Part 4 ==== | + | * goals & principles of DSM evaluation |
| + | * standard evaluation tasks (multiple choice, correlation, | ||
| + | * narrowing down similarity: classifying semantic relations | ||
| + | * systematic large-scale evaluation & its interpretation | ||
| + | * hands-on: // | ||
| + | ==== Part 4: A linguistic perspective on DSMs ==== | ||
| - | ==== Part 5 ==== | + | [[http:// |
| - | <!-- | + | * linguistic evaluation and applications of DSM representations |
| + | * success stories: semantic compositionality, | ||
| + | * issues: non-compositional word meaning, collocational profiles vs. distributional similarity | ||
| + | * free association norms as a window into the mental lexicon | ||
| + | * predicting free associations with DSMs: the FAST task | ||
| + | * practice: // | ||
| - | === Day 3: Which aspects of meaning does a DSM capture? === | ||
| - | [[http:// | + | ==== Part 5 ==== |
| - | [[http:// | + | |
| - | R code: [[http:// | + | |
| - | * evaluation: conceptual coordinates | + | <!-- |
| - | * standard evaluation tasks (multiple choice, correlation, | + | |
| - | * narrowing down similarity: classifying semantic relations | + | |
| - | * practice: // | + | |
| - | + | ||
| - | === Day 4: DS beyond NLP – Linguistic theory === | + | |
| - | + | ||
| - | [[http:// | + | |
| - | [[http:// | + | |
| - | R code: [[http:// | + | |
| - | bonus material: [[http:// | + | |
| - | + | ||
| - | + | ||
| - | * linguistic exploitation of DSM representations | + | |
| - | * a textbook challenge for DSMs: polysemy | + | |
| - | * success stories: semantic compositionality, | + | |
| - | * issues: not all words have a distributional meaning | + | |
| - | * practice: //different exercises with linguistic data sets// | + | |
| === Day 5: DS beyond NLP – Cognitive modelling === | === Day 5: DS beyond NLP – Cognitive modelling === | ||
| Line 79: | Line 71: | ||
| bonus task: [[http:// | bonus task: [[http:// | ||
| bonus material: [[http:// | bonus material: [[http:// | ||
| - | |||
| - | * DSMs for cognitive modelling | ||
| - | * free association norms as a window into the mental lexicon | ||
| - | * predicting free associations with DSMs | ||
| - | * practice: //combining DSMs with first-order co-occurrence for the FAST task// | ||
| --> | --> | ||
