Distributional Semantic Models (NAACL-HLT 2010)

Start page – Schedule – Software & data sets – Bibliography

Presentation slides (PDF, 1.9 MiB) – handout (PDF, 1.0 MiB)

• Introduction
  • motivation and brief history of distributional semantics
  • common DSM architectures
  • prototypical applications

• Taxonomy of DSM parameters including
  • size and type of context window
  • feature scaling (tf.idf, statistical association measures, …)
  • normalisation and standardisation of rows and/or columns
  • distance/similarity measures: Euclidean, Minkowski p-norms, cosine, entropy-based, …
  • dimensionality reduction: feature selection, SVD, random indexing (RI)

• Usage and evaluation of DSM
  • what to do with DSM distances
  • attributional vs. relational similarity
  • evaluation tasks & results for attributional similarity

Part 2 was not covered in the tutorial session at NAACL-HLT 2010. An extended version of the presentation slides & handout is currently in preparation.

• Elements of matrix algebra for DSM
  • basic matrix and vector operations
  • norms and distances, angles, orthogonality
  • projection and dimensionality reduction

• Making sense of DSMs: mathematical analysis and visualisation techniques
  • nearest neighbours and clustering
  • semantic maps: PCA, MDS, SOM
  • visualisation of high-dimensional spaces
  • supervised classification based on DSM vectors
  • understanding dimensionality reduction with SVD and RI
  • term-term vs. term-context matrix, connection to first-order association
  • SVD as a latent class model

• Current research topics and future directions
  • overview of current research on DSMs
  • evaluation tasks and data sets
  • available "off-the-shelf" DSM software
  • limitations and key problems of DSMs
  • trends for future work