One of the questions I have with any direct question-answering system
(another is the MIT START system: http://start.csail.mit.edu/) is what
range of questions can they interpret properly. The easy path to
question-answering is to have a large number of template questions for
common queries: "how high is ***"; "when was *** born"; "who invented ***";
"what is the population of ***"; etc. With a reasonable number of such
templates, perhaps the majority of questions can be **interpreted**
properly, and then the task is to build the KB to include the data. This
can actually be quite useful, but it is, as the article mentions, far from
trying to mimic the capability of human intelligence. (01)
My own interests are in Natural Language Understanding, which I believe
requires something close to the full range of human information-processing
(as contrasted with sensing and motor function) capability - at least at the
level of a five or six-year old. Question-answering systems that depend on
templates and cannot extract information automatically from text can be very
useful and interesting, but probably have little to add to what is already
known about NLU. (02)
The other point I have been advancing is that to get to human-level NLU it
seems now likely to require the full power of a large scientific community
working within a common paradigm of meaning (basic ontology) and language
processing, using open-source data and programs. That is why I am
especially anxious to see some community of reasonable size begin to create
such a paradigm, so that the task does not grind along slowly for another
fifty years in projects of inadequate size that can learn little from each
other because their approaches are too diverse. (03)
May looks like it could be an interesting month. That is when the CALO
project is supposed to be putting some of their results on the Web. After 5
years and 200+ million dollars, I hope it was worth it. (04)
Pat (05)
Patrick Cassidy
MICRA, Inc.
908-561-3416
cell: 908-565-4053
cassidy@xxxxxxxxx (06)
> -----Original Message-----
> From: ontolog-forum-bounces@xxxxxxxxxxxxxxxx [mailto:ontolog-forum-
> bounces@xxxxxxxxxxxxxxxx] On Behalf Of Len Yabloko
> Sent: Monday, March 09, 2009 1:16 PM
> To: [ontolog-forum]
> Subject: Re: [ontolog-forum] Wolfram Alpha
>
> Any predictions?
> (see mine below)
> >
> >Stephen Wolfram, who is an outstanding mathematician, built up
> >the Mathematica system, which is the premier mathematical computing
> >system available. His company has now produced a collection of
> >mathematical models (i.e, ontologies plus reasoning modules that
> >use Mathematica as their foundation) for a wide range of domains.
> >
> >In May, anybody will be able to ask it factual question that can
> >be answered by formal reasoning or computation from material
> >available on the WWW.
> >
> >Following is Wolfram's summary of the project:
> >
> > http://blog.wolfram.com/2009/03/05/wolframalpha-is-coming/
> >
> >Following is a testimonial by someone who has had hands-on
> >experience in testing Wolfram Alpha and was unable to make
> >it fail:
> >
> >http://www.twine.com/item/122mz8lz9-4c/wolfram-alpha-is-coming-and-it-
> could-be-as-important-as-google
> >
> >As the title indicates, the author, Nova Spivack, thinks it could be
> >as important as Google.
> >
> >Following is another comment on Ars Technica:
> >
> >http://arstechnica.com/software/news/2009/03/stephen-wolfram-and-the-
> techno-dianetics-of-google-ology.ars
> >
> >Following is an excerpt from Nova Spivack's note. I strongly
> >agree with it. In fact, I believe that this group must consider
> >Wolfram's approach to be a prime candidate for any system of
> >formal ontologies that might recommend, propose, or adopt.
> >
> >Note that I said *approach*, not the explicit content. I'm sure
> >that the current content of Wolfram Alpha is also valuable, but
> >the techniques they use for developing and using that content
> >should be considered as a basis for further developments.
> >
> >John Sowa
> >_____________________________________________________________________
> >
> >Relationship to the Semantic Web
> >
> >During our discussion, after I tried and failed to poke holes in his
> >natural language parser for a while, we turned to the question of just
> >what this thing is, and how it relates to other approaches like the
> >Semantic Web.
> >
> >The first question was could (or even should) Wolfram Alpha be built
> >using the Semantic Web in some manner, rather than (or as well as) the
> >Mathematica engine it is currently built on. Is anything missed by not
> >building it with Semantic Web's languages (RDF, OWL, Sparql, etc.)?
> >
> >The answer is that there is no reason that one MUST use the Semantic
> Web
> >stack to build something like Wolfram Alpha. In fact, in my opinion it
> >would be far too difficult to try to explicitly represent everything
> >Wolfram Alpha knows and can compute using OWL ontologies and the
> >reasoning that they enable. It is just too wide a range of human
> >knowledge and giant OWL ontologies are too difficult to build and
> curate.
> >
> >It would of course at some point be beneficial to integrate with the
> >Semantic Web so that the knowledge in Wolfram Alpha could be accessed,
> >linked with, and reasoned with, by other semantic applications on the
> >Web, and perhaps to make it easier to pull knowledge in from outside
> as
> >well. Wolfram Alpha could probably play better with other Web services
> >in the future by providing RDF and OWL representations of it's
> >knowledge, via a SPARQL query interface -- the basic open standards of
> >the Semantic Web. However for the internal knowledge representation
> and
> >reasoning that takes places in Wolfram Alpha, OWL and RDF are not
> >required and it appears Wolfram has found a more pragmatic and
> efficient
> >representation of his own.
> >
> >I don't think he needs the Semantic Web INSIDE his engine, at least;
> it
> >seems to be doing just fine without it. This view is in fact not
> >different from the current mainstream approach to the Semantic Web --
> as
> >one commenter on this article pointed out, "what you do in your
> database
> >is your business" -- the power of the Semantic Web is really for
> >knowledge linking and exchange -- for linking data and reasoning
> across
> >different databases. As Wolfram Alpha connects with the rest of the
> >"linked data Web," Wolfram Alpha could benefit from providing access
> to
> >its knowledge via OWL, RDF and Sparql. But that's off in the future.
> >
> >It is important to note that just like OpenCyc (which has taken
> decades
> >to build up a very broad knowledge base of common sense knowledge and
> >reasoning heuristics), Wolfram Alpha is also a centrally hand-curated
> >system. Somehow, perhaps just secretly but over a long period of time,
> >or perhaps due to some new formulation or methodology for rapid
> >knowledge-entry, Wolfram and his team have figured out a way to make
> the
> >process of building up a broad knowledge base about the world
> practical
> >where all others who have tried this have found it takes far longer
> than
> >expected. The task is gargantuan -- there is just so much diverse
> >knowledge in the world. Representing even a small area of it formally
> >turns out to be extremely difficult and time-consuming.
> >
> >It has generally not been considered feasible for any one group to
> >hand-curate all knowledge about every subject. The centralized
> >hand-curation of Wolfram Alpha is certainly more controllable,
> >manageable and efficient for a project of this scale and complexity.
> It
> >avoids problems of data quality and data-consistency. But it's also a
> >potential bottleneck and most certainly a cost-center. Yet it appears
> to
> >be a tradeoff that Wolfram can afford to make, and one worth making as
> >well, from what I could see. I don't yet know how Wolfram has managed
> to
> >assemble his knowledge base in less than a very long time, or even how
> >much knowledge he and his team have really added, but at first glance
> it
> >seems to be a large amount. I look forward to learning more about this
> >aspect of the project.
> >
>
> It has been unusually quite on this forum lately ;-)
> I think the announcement above is a good opportunity to see what this
> community is made of. Is everyone just going to wait for more
> information? Any guesses about what is behind this "miracle". According
> to some believes stated on this forum for years - there got to be some
> "Upper Ontology" involved in this new search engine for it to do what
> is claimed. Or may be, as suggested by others, - a lattice of theories.
> Would't this be a good time for "I told you do". I guess it is safer to
> wait out until all is clear.
> Well, since I have no reputation to risk here, I will venture to say
> that this is another hyped-up promotion for cache-strapped venture.
> Remember when Google started there was no hype - it just came and just
> worked.
>
>
>
>
>
> _________________________________________________________________
> 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
> (07)
_________________________________________________________________
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 (08)
|