Re: [ontolog-forum] Truth

[Gary Berg-Cross <gbergcross@xxxxxxxxx>]

Aldo,

Should I be able to use   Tipalo tool  to create a linked data-rich model for the definitions of Wikipedia entities,get a graphic analysis for an URI like
 http://en.wikipedia.org/wiki/Volcanic_ash#Chemical

It didn't seem to work.

Gary Berg-Cross, Ph.D.  

gbergcross@xxxxxxxxx     

http://ontolog.cim3.net/cgi-bin/wiki.pl?GaryBergCross

NSF INTEROP Project  

http://www.nsf.gov/awardsearch/showAward.do?AwardNumber=0955816

SOCoP Executive Secretary

Knowledge Strategies    

Potomac, MD

240-426-0770

On Mon, Jul 16, 2012 at 8:04 PM, Aldo Gangemi <gangemi@xxxxxxx> wrote:

Dear Leo, John, some comments on the intended usage of FRED.

FRED is intended as a tool for automatic population of the Semantic Web from text, either as a direct, or intermediate representation.

Such tools typically perform shallow parsing (NER, sense tagging, topic detection, some limited relation extraction), which produces sparse triples. Therefore, we try to produce RDF and OWL from the Neo-Davidsonian, DRT-like approach of Boxer's, which is also a very fast tool, compared to deep parsing state of art. Such RDF needs also to be linked, i.e. automatically connected to Semantic Web resources, in order to make such an automatic population useful.

Producing RDF and OWL that makes sense in typical Semantic Web ontologies proved to be a *huge* effort. We had to test dozens of heuristics to arrive at a minimally acceptable result, which is what you are playing with. The work is far from being complete, and many other heuristics are being tested to deal with specific lexical relations, non-standard pseudo-boolean operators, (limited) universal quantification of DRT, etc. You will keep finding less than ideal and some plainly wrong representations, but we wanted anyway to bootstrap this thing, in order to indicate the direction, and to get early feedback. Consider that this is just the basics, what Ferdinand de Saussure called the "in praesentia associations" of words.

What John refers to: metonymy, metaphor, and how basic lexicon is re-described within them, pertains to Saussure's "in absentia associations", and requires deeper heuristics and model training, and something will always be lost. Firstly because no logical language can represent all the subtleties and contextual underpinnings of natural language meaning, and secondly because human meaning is bound to our practices, which are not simply reproducible by machines. But this is a vexata quaestio. 

Our hypothesis is that deep parsing can be useful to a certain extent, as many other approaches are, either statistical or logical. We now have the responsibility to stretch the hypothesis in concrete use cases. An example is the Tipalo tool (http://wit.istc.cnr.it/stlab-tools/tipalo), which creates a linked data-rich model for the definitions of Wikipedia entities, based on FRED.

Best

Aldo

On 14 Jul 2012, at 23:20, John F Sowa wrote:

On 7/14/2012 4:17 PM, Obrst, Leo J. wrote:

on a lark I took your second sentence:

 Indeed, both sides have an interest in channeling their rivalry

 into trade more than weaponry, even as China sees itself as

 increasingly having the upper hand in the region.

and pasted it into FRED ( http://wit.istc.cnr.it/stlab-tools/fred/ ),

which was just released this week

Thanks for the example.  I'm pleasantly surprised that it was able
to do that well.  It illustrates the point that NLP parsing technology
is not bad, even with an ontology that is not adequate for the domain.

But there are huge gaps in the interpretation of what the words refer to
(e.g., China is a place, but by metonomy the intended meaning is the
Chinese government).  And it makes no attempt to analyze the metaphor
of channeling an abstraction like rivalry into some kind of process
(trade) or something physical (weaponry).  And good luck in trying
to interpret the comparative 'more than' that relates them.

By the way, I responded to Chris's complaint by numbering the slides
in the lower right corner.  I also deleted a duplicate slide.  That
causes the final section to start at Slide 51:

   http://www.jfsowa.com/talks/dynolang.pdf

John



_________________________________________________________________
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

_____________________________________

Aldo Gangemi

Senior Researcher

Semantic Technology Lab (STLab)

Institute for Cognitive Science and Technology,

National Research Council (ISTC-CNR) 

Via Nomentana 56, 00161, Roma, Italy 

Tel: +390644161535

Fax: +390644161513

aldo.gangemi@xxxxxx

http://www.stlab.istc.cnr.it

http://www.istc.cnr.it/people/aldo-gangemi

skype aldogangemi

okkam ID: http://www.okkam.org/entity/ok200707031186131660596

_________________________________________________________________
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
 

-- 

_________________________________________________________________
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    (01)