[topicmapmail] Fwd: CPAN release of WordNet::Similarity

[Murray Altheim]

Guy Murphy wrote:
> [snip]
> 
>>I'm curious. How does one define "semantic distance", given that
>>any metric is pretty arbitrary? Is this just a node count between
>>two words based on whatever existing structure is there in the
>>thesaurus?
> 
> [snip]
> 
> Semantics are completely arbitrary to begin with simply representing a
> consensus with regard to meaning, so there's no problem with semantic
> distance being arbitrary as long as people find it useful.
>
> Honestly, I'm not trying to be cute.

Well, cute or not I don't consider consensus as arbitrary. We obviously
find dictionaries and thesauri valuable otherwise we'd not create them,
buy them, use them. I don't think of consensus as universal, but neither
do I think it arbitrary. My skepticism only comes about when it comes
to putting metrics on them, i.e., taking them outside of their initial
human use, using them as input into mathematical (or at least program-
matic functions. E.g., how "semantically far apart" are:

      "dog"  -->  "mammal"
      "dog"  -->  "mammalia"
      "dog"  -->  "canine"
      "dog"  -->  "Canis familiarus"
      "dog"  -->  "Canis domesticus"
      "dog"  -->  "Canis lupus"
      "Canis domesticus"  -->  "Canis lupus"
      "puppy" --> "dog"
      "Poodle" -- "dog"
      "Tony Blair" --> "poodle"
      "Fido" -->  "dog"
      "Dog"  -->  "dog"  (lexically)

where the context in which the statement is made and used play a role?
These are the kinds of real relationships that need to be modeled
accurately if accurate decisions can be made upon the ontological
commitments been made, explicitly or implicitly.

> If you're interesting in semantic distance would you not perhaps find more
> fruit looking at spatial indexing?

I tend to also be skeptical of mappings between semantic and spatial,
as this mixed metaphor brings with it a lot of new issues. And I
don't want any *new* issues... :-)  If you see some value there,
perhaps a ref to a paper you found useful?

Murray

......................................................................
Murray Altheim                  <http://kmi.open.ac.uk/people/murray/>
Knowledge Media Institute
The Open University, Milton Keynes, Bucks, MK7 6AA, UK

    Hunt the Boeing! And test your perceptions!
    http://www.asile.org/citoyens/numero13/pentagone/erreurs_en.htm