Dear Kathryn, (01)
> One can believe there is a single reality without believing there is
> a single universal ontology. (02)
MW: My point precisely. I was obviously a little too enigmatic.
>
> There is a phenomenon known as non-identifiability. Two theories are
> not identifiable if they exactly the same predictions about the
> observable evidence. When theories are not identifiable, then there
> is no scientific way to distinguish which is right. (03)
MW: However, here you are talking about our possible inability to
determine whether one ontology is "true" compared to another, not whether
one actually is.
>
> There is a field of study called Bayesian model averaging, or BMA.
> (Given the multiple meanings of the term "model", in this forum it
> might be better to say Bayesian theory averaging.) We consider a set
> T1, T2, T3, ... of theories. Each makes predictions about the
> observable data. A scientist begins with a prior probability
> distribution: p1, p2, p3, ... where pi is the scientist's probability
> that Ti is the correct theory of reality. The scientist observes
> data. The data may be observational or the result of experimental
> manipulation. We get a series D1, D2, D3, ... of observations.
> After each observation Dk, the scientist updates her probability
> distribution for Ti to its conditional probability given D1, D2, ...
> Dk. Any theory that puts zero probability on what actually happens
> is ruled out immediately. Over time, the scientist puts higher and
> higher probability on theories that are the most consistent with the
> observations.
>
> We can look in the infinite limit at the theories' respective
> calibration agains observations. That is, do x% of the things to
> which Ti assigns probability x come true? There are more complicated
> tests -- we can look not just at frequencies of individual
> observations, but of sequences of observations, or observations
> picked out by some criterion. We say a theory agrees with the data
> if it passes all the statistical tests we care to throw at it.
>
> If only one of the theories agrees with the data, then in the
> infinite limit as more and more observations are obtained, the
> posterior probability of that theory will converge to 1. If two or
> more theories agree, then the probability of the most parsimonious
> will converge to 1, where parsimonious means having the fewest
> adjustable parameters. This is known as the "natural Ockham's razor"
> of Bayesian model averaging. If two theories agree with the data and
> are equally parsimonious, then in the infinite limit, both may have
> positive probability, and the probability assigned to each theory
> will depend on the prior probability the scientist assigned to it.
>
> Now consider two Bayesians who are doing Bayesian model averaging on
> the same set of theories. If there is a single most parsimonious
> theory that agrees with the data, both Bayesians will come to agree
> with high probability that this theory is the correct one. If there
> is more than one equally parsimonious theory that all agree with the
> data, the two Bayesians will come to agree that one of these theories
> is correct, but they may have arbitrarily great disagreements over
> which is the correct one -- one of them may end up almost sure that
> Ti is correct, while the other one is equally sure that Tj is correct.
>
> Ontologies, and scientific theories, are DESCRIPTIONS of reality.
> One can believe there is a single, correct, actual way things really
> truly are, without believing that there is a single, uniquely correct
> way to DESCRIBE the way things really truly are. If two ontologies
> have identical observable implications, and are equally parsimonious,
> their proponents can yell at each other till the cows come home, and
> there will be no way to tell who is right. (04)
MW: Again, my point precisely. (05)
MW: Actually, it is not that hard (but hard enough) to develop an
ontology that is "not wrong", but achieves this by leaving out some
detail. An extreme example of this is the ontology that consists of
the assertion "there are things", which I hope would be relatively
uncontroversial. Unfortunately the more detail you add, the higher
the chance you get something "wrong".
>
> Kathy
>
>
> At 9:25 AM +0100 7/22/07, matthew.west@xxxxxxxxx wrote:
> >Dear Azamat and others,
> >
> >I agree with Azamat - there is a single universal ontology.
> >(Just because I believe there is a single reality).
> >
> >Unfortunately, I can see there are a lot of other ontologies
> >too, and it seems hard to determine which is the right one
> >(and I doubt it is available to be discerned yet).
> >
> >Regards
> >
> >Matthew West
> >Reference Data Architecture and Standards Manager
> >Shell International Petroleum Company Limited
> >Registered in England and Wales
> >Registered number: 621148
> >Registered office: Shell Centre, London SE1 7NA, United Kingdom
> >
> >Tel: +44 20 7934 4490 Mobile: +44 7796 336538
> >Email: matthew.west@xxxxxxxxx
> >http://www.shell.com
> >http://www.matthew-west.org.uk/
> >
> >
> >> -----Original Message-----
> >> From: ontolog-forum-bounces@xxxxxxxxxxxxxxxx
> >> [mailto:ontolog-forum-bounces@xxxxxxxxxxxxxxxx]On Behalf Of Azamat
> >> Sent: 21 July 2007 23:02
> >> To: [ontolog-forum]
> >> Subject: Re: [ontolog-forum] Terminology Question concerningWeb
> >> Architecture and LinkedData
> >>
> >>
> >> Patrick Durusau wrote: I am sure Azamat will formulate his
> >> own response but
> >> I can answer for
> >> myself since I share the opinion that there is no "universal
> >> ontology."
> >>
> >> Dear Patrick,
> >> Let me just ensure you that there is a ''universal
> >> ontology'', '' global
> >> ontology'', '' master ontology'', or '' standard ontology'', as a
> >> comprehensive consistent world model.
> >> Otherwise, no Semantic Web, no artificial intelligent
> systems, etc.
> >> Azamat
> >> http://www.eis.com.cy
> >>
> >>
> >> Patrick
> >> ----- Original Message -----
> >> From: "Patrick Durusau" <patrick@xxxxxxxxxxx>
> >> To: "[ontolog-forum]" <ontolog-forum@xxxxxxxxxxxxxxxx>
> >> Sent: Sunday, July 22, 2007 12:23 AM
> >> Subject: Re: [ontolog-forum] Terminology Question concerning Web
> >> Architecture and LinkedData
> >>
> >>
> >> > Randall,
> >> >
> >> > Randall R Schulz wrote:
> >> >> On Saturday 21 July 2007 12:59, Azamat wrote:
> >> >>
> >> >>> Rarely have i seen such obtusness. Pat has said many
> interesting
> >> >>> things, but this statement reflects the whole point of
> >> the Semantic
> >> >>> Web. No Real Meanings, no Semantic Web, or no Universal
> >> Ontology,
> >> >>> no Intelligent Web. That's it.
> >> >>>
> >> >>> Azamat
> >> >>>
> >> >>
> >> >> If this is the statement it seems to be, namely one of complete
> >> >> pessimism about the entire Semantic Web endeavor (and
> >> apparently, any
> >> >> form of computational intelligence), what motivates your
> >> participation
> >> >> in this forum?
> >> >>
> >> >>
> >> > I am sure Azamat will formulate his own response but I can
> >> answer for
> >> > myself since I share the opinion that there is no
> >> "universal ontology."
> >> >
> >> > First, I don't think belief in a universal ontology has
> >> anything to do
> >> > with "computational intelligence." It certainly is
> irrelevant to any
> >> > claims of human intelligence, the possessors of which have been
> >> > demonstrated to believe in any number of ontologies,
> perhaps even
> >> > contradictory ones.
> >> >
> >> > Second, and more pragmatically, if a client finds that use
> >> of "Semantic
> >> > Web" technologies provides a useful result for whatever
> purpose they
> >> > have in mind, what is their (or my) belief in a universal
> >> ontology have
> >> > to do with it? Or the connection of such a universal
> >> ontology to "real"
> >> > meaning? Interesting questions for a coffee shop
> discussion but has
> >> > little to do with the results that motivate clients to pay
> >> for services.
> >> >
> >> > I say all that because the topic maps community has spent
> >> years (not as
> >> > many as the ontology community) hand wringing over the
> >> "big" issues when
> >> > the real questions that needed answering were what result
> >> does the use
> >> > of topic maps enable that isn't otherwise available and how
> >> does than
> >> > answer the needs of user X?
> >> >
> >> > Granted, I take that position because I think meaning is in
> >> the eyes of
> >> > the user (cf. reader response criticism and Stanley
> Fish) but I also
> >> > suspect that pragmatically speaking, the question that
> any semantic
> >> > technology has to answer is of what use is it to the user
> >> in question?
> >> > It's formal correctness and answering the "big" questions
> >> won't save a
> >> > technology that has no real payoff for users.
> >> >
> >> > I participate because I wanted to learn the terminology
> and thinking
> >> > that underlies current ontology efforts. Whether those
> efforts are
> >> > "true" in some absolute sense of the world isn't a question
> >> that I worry
> >> > about. How those efforts may or may not have benefits for users,
> >> > however, is a question that concerns me.
> >> >
> >> > Hope you are having a great day!
> > > >
> >> > Patrick
> >> >
> >> >> Randall Schulz
> >> >>
> >> >>
> _________________________________________________________________
> >> >> Message Archives: http://ontolog.cim3.net/forum/ontolog-forum/
> >> >> Subscribe/Config:
> >> 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 Post: mailto:ontolog-forum@xxxxxxxxxxxxxxxx
> >> >>
> >> >>
> >> >>
> >> >>
> >> >
> >> > --
> >> > Patrick Durusau
> >> > patrick@xxxxxxxxxxx
> >> > Chair, V1 - US TAG to JTC 1/SC 34
> >> > Acting Convener, JTC 1/SC 34/WG 3 (Topic Maps)
> >> > Co-Editor, ISO/IEC 13250-1, 13250-5 (Topic Maps)
> >> > Co-Editor, OpenDocument Format (OASIS, ISO/IEC 26300)
> >> >
> >> >
> >> >
> _________________________________________________________________
> >> > Message Archives: http://ontolog.cim3.net/forum/ontolog-forum/
> >> > Subscribe/Config:
> >> 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 Post: mailto:ontolog-forum@xxxxxxxxxxxxxxxx
> >> >
> >>
> >>
> >> _________________________________________________________________
> >> Message Archives: http://ontolog.cim3.net/forum/ontolog-forum/
> >> Subscribe/Config:
> >> 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 Post: mailto:ontolog-forum@xxxxxxxxxxxxxxxx
> >>
> >>
> >>
> >
> >
> >_________________________________________________________________
> >Message Archives: http://ontolog.cim3.net/forum/ontolog-forum/
> >Subscribe/Config:
> 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 Post: mailto:ontolog-forum@xxxxxxxxxxxxxxxx
> >
>
>
> _________________________________________________________________
> Message Archives: http://ontolog.cim3.net/forum/ontolog-forum/
> Subscribe/Config:
> 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 Post: mailto:ontolog-forum@xxxxxxxxxxxxxxxx
>
>
> (06)
_________________________________________________________________
Message Archives: http://ontolog.cim3.net/forum/ontolog-forum/
Subscribe/Config: 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 Post: mailto:ontolog-forum@xxxxxxxxxxxxxxxx (07)
|