Thread Links Date Links
Thread Prev Thread Next Thread Index Date Prev Date Next Date Index

RE: SUO: WordNet Mappings



Hi John,

	We're focusing on the nouns initially.  First, nouns are clearly
favored in WordNet -  there is much more information about nouns that there
is about other parts of speech.  The second reason is that most verbs have a
nominal form, so that mapping all of the nouns gives you most of the verbal
meanings.  Of course, it would be nice to have a pointer from the noun
synset to the corresponding verb synset, and I hope the WordNet people will
introduce this at some point.

	As for your point about organisation, I agree that the structure of
Word leaves something to be desired in terms of logical rigor (or course,
the database was intended to be a model of lexical memory, rather than a
formal ontology, so that's not a criticism).  However, we are not using this
structure in our mapping work.  We are associating individual synsets with
SUMO concepts.  

	I'm attaching a paper about the mapping project, in case you'd like
more detail.

-Ian 



> -----Original Message-----
> From: John Bateman [mailto:bateman@uni-bremen.de]
> Sent: Wednesday, August 22, 2001 1:14 AM
> To: Ian Niles
> Cc: Standard-Upper-Ontology (E-mail)
> Subject: Re: SUO: WordNet Mappings
> 
> 
> > A while back, I mentioned our project of mapping the SUMO to the
> > noun synsets in WordNet.  We've now loaded the first 1000 
> or so mappings
> > into our ontology browser
> 
> Why the nouns? Surely the verbs are going to be *much* more 
> interesting.
> Are you going to do those too? There are a host of more to 
> less damning
> criticisms of the WordNet "organisation".... what about the 
> EuroWordNet
> upper structure? Is that going to be done too? (Again for the 
> verbs would
> be most interesting).
> 
> Hopefully,
> 
> John Bateman.
> 
> 

SUMO-WN.doc