[Corpora-List] (no subject)

[Sandra Kuebler]

Hi,

Maybe this answer is too obvious: Why not use Kullbach-Leibler  
divergence (cf. e.g. Manning & Schuetze, 1999, ch. 2.2.5)? It's often  
used as a distance metric.

Sandra


On Oct 23, 2007, at 11:17 AM, ddg at di.ubi.pt wrote:

> Dear Colleagues,
>
> We are looking for asymetric similarity measures in the context of
> automatic construction of ontology from the web. I think I saw one  
> paper
> at ACL 2007 talking about this, but can not find it anymore :-(
>
> Could someone give us a clue on this topic?
>
> Thanks in advance.
>
> Gaël.
>
>
> ---------------------------------------------------------
> Gaël Harry Dias, PhD            | Assistant Professor
> Human Language Technology Group | [hultig.di.ubi.pt]
> Computer Science Department     | [www.di.ubi.pt/~ddg]
> Beira Interior University       | [ddg at di.ubi.pt]
> 6201-001 - Covilhã              | [Tel: +351 275 319 891]
> PORTUGAL                        | [Fax: +351 275 319 899]
> ---------------------------------------------------------
>
> _______________________________________________
> Corpora mailing list
> Corpora at uib.no
> http://mailman.uib.no/listinfo/corpora

Sandra Kuebler
Indiana University
Department of Linguistics
Memorial Hall 322
1021 E. Third Street
Bloomington IN 47405
USA
phone: (812) 855-3268
fax: (812) 855-5363
email: skuebler at indiana.edu



-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/corpora/attachments/20071023/9c368898/attachment.htm>
-------------- next part --------------
_______________________________________________
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora