John, (01)
Happy Chinese National Day. (02)
On Fri, Sep 30, 2011 at 2:23 PM, John F. Sowa <sowa@xxxxxxxxxxx> wrote:
>
> The distinction I was trying to make is between a symbolic knowledge
> representation, which can be translated to and from a natural language... (03)
Had anyone ever found a way to do that using logic, your argument
might hold water. (04)
I personally worked for years on an MT system which attempted this. We
did not succeed. No-one has succeeded since. (05)
Humans may be able to get back and forth to a useful degree, but it is
exactly how they do that which is at issue. (06)
Sure, once we figure out the mechanism behind the necessary subjective
judgments, it may be desirable to express the relevant meaning in one
or other logic. (07)
But no one logic can in itself express all the distinctions necessary
to make the choice. (08)
> Formalisms that cannot be translated to English in a meaningful way
> are the weights on the nodes of a neural network. You can explain
> how those weights were computed, but it is not possible to derive
> a sentence or phrase that could be used as an explanation of what
> any particular node "means".
>
> Another example is a vector that counts the co-occurrences of words
> in various documents. You can point to any particular number and
> say that it states the number of times word A and word B occurred
> in the same document. But that doesn't have any kind of intuitive
> meaning that you can state as an English sentence.
>
> Then if you take those vectors and apply the SVD algorithms to
> reduce the dimensionality, you get a string of numbers whose
> meaning is totally opaque. All you can say is that the vector
> represents "something" that is related to the meaning of the word. (09)
John, I'll try to cut you a break. All this, its like saying TV will
never work, because if you look at any pixel it has no picture. (010)
You're confusing the means with the ends. Distributed representation
can be impenetrable, but that doesn't mean it can't be used to
represent logic, and do so more flexibly than logic itself. (011)
I agree little has been done historically to implement
compositionality in particular using distributed representation. That
doesn't mean it can't be done. That is what these recent papers are
addressing. (012)
My implementation may have long lists of numbers, but once it folds
them all together you get nice intuitively reasonable hierarchies, a
parse structure in fact. You can map the vectors subjectively to
symbols. I think it would be possible to map it to any logic you want. (013)
>> I grant you quantum variables imply a certain randomness. Though I
>> think that randomness is actually just subjectivity too.
>
> This has nothing to do with subjectivity. (014)
That's a very flat categorical statement. I read on several lines
before I realized it had no supporting argument. (015)
To get started on my point of view anyone interested can google "the
observer in quantum mechanics". (016)
E.g: (017)
"In quantum mechanics, the observer and the system being observed
became mysteriously linked so that the results of any observation
seemed to be determined in part by actual choices made by the
observer."
http://www.grc.nasa.gov/WWW/k-12/Numbers/Math/Mathematical_Thinking/observer.htm (018)
-Rob (019)
_________________________________________________________________
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 (020)
|