[Corpora-List] CPAN release of WordNet::Similarity

[ted pedersen]

We are pleased to announce the CPAN release of the WordNet::Similarity
package. This is a significant upgrade to our previous Distance packages.

You can find WordNet::Similarity (including README) at:

http://search.cpan.org/author/SID/WordNet-Similarity-0.03/

This package consists of Perl modules along with supporting Perl programs
that implement the semantic similarity measures of Leacock-Chodorow
(1998), Jiang-Conrath (1997), Resnik (1995), Lin (1998), Hirst-St Onge
(1998) and Banerjee-Pedersen (2002). The package contains Perl modules
designed as object classes with methods that take as input two word
senses from WordNet. These methods can be embedded in any Perl program
and will return the semantic similarity between the senses according to
the requested measure.

There are also support programs for generating information content values
(Resnik 1995) for WordNet concepts from a variety of corpora, including
the BNC, Penn Treebank, Semcor, or any raw text provided by a user. The
information content values are required by the measures of Jiang-Conrath,
Lin, and Resnik, and could also be useful in a wide range of WordNet based
applications.

The package also provides a simple command line interface that returns the
similarity measure of two given words. This is very similar to our
earlier version of the Distance package. A number of switches and options
have been provided to enhance the output with trace data and other
information.

Please download and give Similarity a try! We anxiously await your
feedback and suggestions.

Thanks,
Sid and Ted

--
# Ted Pedersen                              http://www.umn.edu/~tpederse #
# Department of Computer Science                        tpederse at umn.edu #
# University of Minnesota, Duluth                                        #
# Duluth, MN 55812                                        (218) 726-8770 #