Hi Fred

Frederick Giasson a écrit :
> Hi Bernard,
>
> Well, if humans are typed has Queen102313008; it is indeed shocking :)
It is!

http://dbpedia.org/page/Queen_Silvia_of_Sweden
http://dbpedia.org/page/Cleopatra_VII
definitely human

http://dbpedia.org/page/Galadriel
if you don't mind the pointed ears she looks more human than many 
creatures I've met in my life and which called themselves so.  :-)
>
> Some backgrounds of the issue here:
>
> This queen refers to this WordNet word sense:
>
> {02313008} [05] S: 
> <http://wordnet.princeton.edu/perl/webwn?o2=&o0=1&o7=1&o5=1&o1=1&o6=&o4=&o3=1&s=queen&i=0&h=000000000000#c>
>  
> (n) *queen#1* (the only fertile female in a colony of social insects 
> such as bees and ants and termites; its function is to lay eggs)
>
> That is an insect.
Indeed.
>
> The problem is not with Yago, but potentially with its integration 
> into DBPedia (I didn't investigated further than by reading your mail).
Certainly. Typical vocabulary clash ...
>
> What one have to take into account when using Yago is that these 
> concepts (as Queen) come from WordNet, so one concept has, in most of 
> the cases, more than one word sense. Word senses are tagged with the 
> WordNet word sense number (0231....).
Understood. I'm sure DBpedia team is aware of those homonymy issues and 
will improve the extraction to handle them more correctly in future 
versions.

Bernard

<http://mondeca.wordpress.com/>



-------------------------------------------------------------------------
Check out the new SourceForge.net Marketplace.
It's the best place to buy or sell services for
just about anything Open Source.
http://ad.doubleclick.net/clk;164216239;13503038;w?http://sf.net/marketplace
_______________________________________________
Dbpedia-discussion mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/dbpedia-discussion

Reply via email to