Matt Mahoney wrote:
I am interested in identifying barriers to language modeling and how to
overcome them.
I have no doubt that probabilistic models such as NARS and Novamente can
adequately represent human knowledge. Also, I have no doubt they can
learn e.g. relations such as "all frogs are green" from examples of
green frogs. My question relates to solving the language problem: how
to convert natural language statements like "frogs are green" and
equivalent variants into the formal internal representation without the
need for humans to encode stuff like (for all X, frog(X) => green(X)).
This problem is hard because there might not be terms that exactly
correspond to "frog" or "green", and also because interpreting natural
language statements is not always straightforward, e.g. "I know it was
either a frog or a leaf because it was green".
>
>
Converting natural language to a formal representation requires language
modeling at the highest level. The levels from lowest to highest are:
phonemes, word segmentation rules, semantics, simple sentences, compound
sentences. Regardless of whether your child learned to read at age 3 or
not at all, children always learn language in this order.
And the evidence for this would be what?
There is plenty of evidence that they do not learn in this order: they
are still learning phonemes in parallel with semantics, they grasp some
semantics before any verbal language (Justin Corwin pointed out the baby
sign language issue, and that reminded me that we did exactly that with
our son: he had several signs by about 6 months, and produced his first
word at 10 months, so clearly he had something like the "semantics"
(whatever that means) before any spoken language whatsoever). Some
children come out with compound sentences from the get-go.
The overall story is: NO separable stages at all. Everything overlaps.
And in adult humans, as I mentioned earlier, language understanding (at
least) clearly has overlapping, cascaded stages.
Richard Loosemore.
-----
This list is sponsored by AGIRI: http://www.agiri.org/email
To unsubscribe or change your options, please go to:
http://v2.listbox.com/member/[EMAIL PROTECTED]
