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. The toolkit consists of two
sub-systems, implemented in Perl (www.perl.com) and R (www.r-project.org),
respectively. Data sets 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
is provided by the UCS/R system .
Version 0.3.2 is now available and can be downloaded from
http://www.collocations.de/software.html
For those of you who have been interested in UCS but haven't had enough round
tuits to give it a try, now would be an excellent time to get started: the new
release comes with full documentation (printed as well as on-line) and
tutorials for both UCS/Perl and UCS/R.
Enjoy!
Stefan Evert.
PS: I'm not tracking downloads, so all I know is that I have at least one user
(beside myself :o), plus all the people he's made work with UCS, too. I'd
like to hear from anyone else who's tried the toolkit - experiences, feedback,
problems, suggestions. Should there be a few active users, it might be
worthwhile to set up a UCS mailing list. So come forward, and let me know
what you think.
This archive was generated by hypermail 2b29 : Tue Jul 13 2004 - 11:00:16 MET DST