[Corpora-List] software semantic similarity between texts

J Washtell lec3jrw at leeds.ac.uk
Tue Oct 21 18:42:07 CEST 2008


It's not software as such, but you might find it interesting to take a look at Kireyev (2008) "Beyond words: Semantic Representation of Text in Distributional Models of Language", in Proceedings of the ESSLLI 2008 Lexical Semantics Workshop:



Justin Washtell University of Leeds

Quoting Dom Widdows <widdows at google.com>:

> SemanticVectors has a CompareTerms class you can call from the command
> line that lets you compare two passages (rather than individual words)
> just by using quotes.
> I'm sure other tools can be convinced to do this as well reasonably
> easily (but it's nice if it's already there).
> Best wishes,
> Dominic
> On Mon, Oct 20, 2008 at 11:08 AM, Antonio Toral
> <antonio.toral at ilc.cnr.it> wrote:
>> Thanks Eric!
>>> WordNet::Similarity (http://wn-similarity.sourceforge.net/)
>>> "... is a Perl module that implements a variety of semantic similarity
>>> and relatedness measures based on information found in the lexical
>>> database WordNet."
>> That's right, but WordNet::Similarity performs semantic similarity between
>> pairs of words whereas I need to get semantic similarity between
>> short texts.
>> _______________________________________________
>> Corpora mailing list
>> Corpora at uib.no
>> http://mailman.uib.no/listinfo/corpora
> _______________________________________________
> Corpora mailing list
> Corpora at uib.no
> http://mailman.uib.no/listinfo/corpora

More information about the Corpora mailing list