airhead-research


The S-Space Package: A scalable software library for semantic spaces

Project Overview

The S-Space Package is a collection of algorithms for building Semantic Spaces as well as a highly-scalable library for designing new distributional semantics algorithms. Distributional algorithms process text corpora and represent the semantic for words as high dimensional feature vectors. These approaches are known by many names, such as word spaces, semantic spaces, or distributed semantics and rest upon the Distributional Hypothesis: words that appear in similar contexts have similar meanings.

The research and development is being done by the Natural Language Processing group at UCLA led by David Jurgens and Keith Stevens, under the advisory of Dr. Michael Dyer.

We have moved!

The S-Space Package is now hosted on GitHub at https://github.com/fozziethebeat/S-Space. The Google Code site will be left for posterity, but please see the new GitHub site for up-to-date documentation and code! Click here to go directly to downloading the new code. Also, the S-Space Package is now Mavenized, so please add the following to use the package as a dependency <dependency> <groupId>edu.ucla.sspace</groupId> <artifactId>sspace</artifactId> <version>2.0</version> </dependency> ( note: Check the GitHub page to see what all versions are available)

The Google Groups discussion will still remain, so please keep the comments and feature requests coming!