[Corpora-List] Faster tool for WordNet Similarity measures

[Hagen Fürstenau]

Hi,

> I should also say that a number of people have said they were going to
> try and do this sort of pre-computation of values, but I can't recall
> if anyone actually finished that and/or made it available. If so that
> could be something to consider (and it might be nice for anyone who
> has done that to remind us as it might be generally pretty useful).

I implemented Jiang-Conrath similarity as a C extension for Python. It's
pretty fast, processing about 240,000 noun pairs a second on my 3GHz
machine, and only requires a precomputed structure of about 26MB.

It's available at:
http://www.coli.uni-saarland.de/~hagenf/software/svectors/

It also computes dot products on sparse vectors. As this was the
by-product of some other work, there's not much in the way of
documentation, only a demo script in Python.

I don't know if this is of any help to Suzan, whose problem seem to be
start up times, but maybe it's useful to someone else.

Cheers,
Hagen


-- 
http://www.coli.uni-saarland.de/~hagenf/

_______________________________________________
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora