Distributional Semantic Models (ESSLLI 2009)

Start page – Schedule – Software & data sets – Bibliography

Schedule & handouts

Credits: Some of the slides in the course are based on an earlier DSM course taught by Marco Baroni

Introduction

Foundations of DSMs (Mon, 27 July)

general introduction & background
DSMs in a nutshell
the DSM parameter space: a taxonomy

Slides, Handout

Matrix algebra & vector spaces (Tue, 28 July)

matrix representation, foundations of matrix algebra
geometric analysis (norms, distances, similarity & angles)
implementation: R as an interactive DSM laboratory

Slides, Handout – DSM lab (R script), bnc_vobj_filtered.txt.gz (15 MB) – Homework (R script), potter_tokens.txt.gz (8.9M)

DSMs in computational linguistics and cognitive science (Wed, 29 July)

What can we do with DSM vectors?
Do DSMs capture interesting aspects of word meaning?

Slides, Handout, Concrete nouns clustering, Concrete nouns MDS

Geometric interpretation of DSM spaces (Thu, 30 July)

more advanced matrix algebra
distances, norms and angles
principal components analysis (PCA) as noise reduction

Slides, Handout

SVD (Fri, 31 July, part A)

singular value decomposition (SVD)
managing high-dimensional DSMs (SVD, random indexing)

Slides, Handout

Challenges for DSMs & current research (Fri, 31 July, part B)

looking for a unified model
DSMs and compositionality

Slides, Handout