Re: THEORY: Parsing for meaning.

--- Yahya Abdal-Aziz <yahya@...> wrote:

<snip>
>
>
> Gary, the technique seems promising.  Some
> questions for you:
>
> 1.  How do you know how to decompose, eg,
> > --little monkey--. (Pattern adj+noun)
> > 	=> Same monkey is little
>
>  - is it by rules, categories or sheer statistical
> "occurrence in context" ie of one word in a pattern
> of other words?
>
> 2.  Does your pattern matching system *need* the
> categories of "noun" and "adjective"; or is naming
> these categories just a shorthand way by which
> humans can express and recognise a pattern or
> range of patterns?
>
> 3.  What makes you think the decompositions will be
> unique?
>
> 4.  Should they be?
>
> 5.  Do you have a closed set of primitive relations
> in mind, such as "belong_to", "be_in", etc?
> (Probably
> not, if you need such things as "be_bound_to".)
>
> 5a.  If so, what are they?
>
> 5b.  If not, how do you propose to create the
> relations necessary to parse an utterance?
>
This idea is still pretty much half-baked so I don't
have a lot of answers yet, but here's my thoughts on
your questions:

1. The database of words and patterns would be HUGE,
and somewhere in that database would be something to
the effect of "little -> adj(little)" and "monkey ->
anim(monkey)" where the class "anim" is derived from
the class of objects in general and would be matched
by the pattern "adj(*) obj(*) -> <obj> is <adj>".

2. I probably wouldn't use "standard" catgeories, but
would allow the categories to emerge based on
interchangability. Also certain categories would be
necessary to validate the parsing process as it
proceeds. For example the category "person" might be
different from the category "Animate Object" because
certain verbs (like "speak") that can be used with
objects of type "person" can't logically be used with
objects of a different category. "Person" would
naturally include personified non-human objects
(Mickey Mouse) and other sentient beings (Klingons).

3. and 4. I don't know.

5. The primatives would emerge from the corpus as the
patterns are collected. That's still all very vague
and undefined.

--gary

Reply