The UCS toolkit.

The UCS toolkit is a collection of libraries and scripts for the statistical analysis of cooccurrence data. Data sets – each one containing a list of word pairs together with their joint and marginal frequencies – are stored in a tabular format in plain (compressed) text files. They can be viewed, printed, manipulated in various ways, annotated with association scores from a wide range of built-in measures, ranked, and sorted with the UCS/Perl system. Additional functionality for the graphical evaluation of association measures in a collocation extraction task (cf. Evert & Krenn, 2001) is provided by the UCS/R system.

Download UCS version 0.5 (pre-release) (UCS-0.5-prerelease.tar.gz, 1.9M) - What's new?

• Note: UCS version 0.5 will be the official release to accompany my PhD thesis, including scripts and data sets that allow you to reproduce most of the experiments, tables and graphs in the thesis. This pre-release version has been provided to fix certain compatibility issues with Mac OS X and recent versions of R.

On-line documentation: UCS/Perl documentation - UCS/R documentation
On-line tutorials: UCS/Perl tutorial - UCS/R tutorial - Viktor Trón's UCS quickstart (a one-minute guide for programmers)

Requirements

• Perl version 5.6.1 or newer [http://www.perl.com/]
• Additional Perl modules [http://www.cpan.org/]
  • Expect
  • Pod::Perldoc (Perl versions prior to 5.8.1)
  • Perl/Tk and Tk::Pod (recommended)
  • Term::ReadKey (recommended)
• The R statistical environment version 1.6 or newer (version 2.0 or newer recommended) [http://www.r-project.org/]
  • RSPerl interface [http://www.omegahat.org/RSPerl/] for faster communication between Perl and R
    (RSPerl may be difficult to install, and is not required for running UCS)
• a2ps (recommended)

NB: Future releases of the UCS toolkit are expected to require Perl version 5.8.0 or newer (for Unicode support) and may also require R version 1.9.0 or newer.

Supported and tested platforms

• Linux 2.4 / i386 (SuSE 9.0 & RedHat 9)
• SUN Solaris 2.8 / SPARC
• Mac OS X 10.4.8 / PowerPC
• other Unix-like platforms should work as well [not tested]
• Win32 / i386 (Cygwin emulation) [experimental]

Copyright © 2004-2006 by Stefan Evert.

Footnote: The UCS toolkit has been designed for scientific research on the properties of statistical association measures and the relation between cooccurrences and collocations. In my terminology, this involves a close look at the data and a thorough understanding of the theoretical and methodological background. Flexibility is more important than either frills or speed. Therefore, the UCS system is not intended as a number cruncher that extracts and processes cooccurrences from several hundred million words of text in a few minutes. Nor is it a black box that accepts text files from a word processor and produces a list of collocation candidates at the push of a button.

Archive: UCS-0.4.tar.gz (1.7M) - UCS-0.3.2.tar.gz (1.6M) - UCS-0.3.1.tar.gz (465k) - UCS-0.3.tar.gz (463k) - UCS-0.2.tar.gz (440k)