Re: [ontolog-forum] Ontologies for hybrid connectionist-semantic systems

["Obrst, Leo J." <lobrst@xxxxxxxxx>]

Yes, PR-OWL is a fusion of OWL + Bayesian Semantics, and is the result of Paulo Costa’s GMU dissertation. However, the foundation was laid in Kathy Laskey’s multi-entity Bayesian networks (MEBN) work, which is a FOL + probability formalism.

 

See:

 

Costa, Paulo; Kathryn Blackmond Laskey. 2006. PR-OWL: A Framework for Probabilistic Ontologies. Proceedings of the Fourth International Conference on Formal Ontology in Information Systems. November 2006. http://ite.gmu.edu/~klaskey/papers/FOIS2006_CostaLaskey.pdf.

 

http://pr-owl.org/mebn/index.php.

 

Also, the URL Simon provided http://www.pr-owl.org/index.php has most of the references.

 

Thanks,

Leo

 

_____________________________________________

Dr. Leo Obrst        The MITRE Corporation, Information Semantics

lobrst@xxxxxxxxx     Information Discovery & Understanding, Command & Control Center

Voice: 703-983-6770  7515 Colshire Drive, M/S H305

Fax: 703-983-1379    McLean, VA 22102-7508, USA

 

 

From: ontolog-forum-bounces@xxxxxxxxxxxxxxxx [mailto:ontolog-forum-bounces@xxxxxxxxxxxxxxxx] On Behalf Of Simon Spero
Sent: Friday, December 03, 2010 6:45 PM
To: [ontolog-forum]
Subject: Re: [ontolog-forum] Ontologies for hybrid connectionist-semantic systems

 

I don't know how close this gets to what's being asked for, but Paul Costas's work on PR-OWL might be relevant. See e.g. http://www.pr-owl.org/index.php

I don't know if this specific proposal is being actively developed?

Simon

On Dec 3, 2010 6:09 PM, "John F. Sowa" <sowa@xxxxxxxxxxx> wrote:
> On 12/3/2010 5:48 PM, John Bottoms wrote:
>> IBM has made significant progress with a hybrid system that incorporates
>> semantic and statistical analysis to find answers to Jeopardy questions.
>> ...
>> Could this be done within OWL by masquerading or encapsulating?
>> Or would a new structure be required?
>
> The short answer is no.
>
> OWL was deliberately limited in capability, and it was designed for
> processing RDF data.
>
> AI projects such as IBM's system, Cyc, our VivoMind work, and many
> other systems for NLP use much richer and more complex knowledge
> representation and reasoning systems than OWL. And they use far
> more efficient data representations than RDF.
>
> OWL was never designed for AI or NLP.
>
> John Sowa
>
> _________________________________________________________________
> Message Archives: http://ontolog.cim3.net/forum/ontolog-forum/
> Config Subscr: http://ontolog.cim3.net/mailman/listinfo/ontolog-forum/
> Unsubscribe: mailto:ontolog-forum-leave@xxxxxxxxxxxxxxxx
> Shared Files: http://ontolog.cim3.net/file/
> Community Wiki: http://ontolog.cim3.net/wiki/
> To join: http://ontolog.cim3.net/cgi-bin/wiki.pl?WikiHomePage#nid1J
> To Post: mailto:ontolog-forum@xxxxxxxxxxxxxxxx
>

_________________________________________________________________
Message Archives: http://ontolog.cim3.net/forum/ontolog-forum/  
Config Subscr: http://ontolog.cim3.net/mailman/listinfo/ontolog-forum/  
Unsubscribe: mailto:ontolog-forum-leave@xxxxxxxxxxxxxxxx
Shared Files: http://ontolog.cim3.net/file/
Community Wiki: http://ontolog.cim3.net/wiki/ 
To join: http://ontolog.cim3.net/cgi-bin/wiki.pl?WikiHomePage#nid1J
To Post: mailto:ontolog-forum@xxxxxxxxxxxxxxxx    (01)