I like Hausser’s system but it does not solve the kinds of problems that I
need to solve.  His left associative system with the pointer or address to
other parts of associated speech certainly seem more sensible then the
grammars that use a method of direct substitution to determine whether the
formation of a sentence is grammatical.  But I am more interested in the
meaning of sentences and I believe that there is too much that the theories
of elementary formal grammar have not solved.  I haven’t finished the paper
that Hausser sent but I will get back to it in a few weeks.



I believe that the initial interpretation of sentences partly relies on the
meaning and roles of words that can be learned but which are not
necessarily found from within a strict partitioning of the constituents and
elements and fundamental systems of the grammar.  So, just as Hausser’s
grammar seems a little more sensible than the strictly substitutional
generative grammars, I believe that we need to find a way to combine more
from semantics into the initial stages of recognition.  These rules should
be largely associative and could be expressed as substitutions, but they
may not be found from a conventional analyses of how these fundamental
systems may be generated.  So the most unconstrained system of formal
generative grammar might be needed to express the range of human language
but once the grammatical sentences of the language were found it might turn
out that they can be expressed by simpler systems.  The conclusion of my
thought on this would be to say that we need a greater freedom to discover
the relationships between words and phrases to discover how words are used
to govern the discovery of the meaning of the expressions.  Words and
phrases are used to convey ideas but they also convey the instructions on
how to encode and decode the words and phrases of the expressions used.  Formal
generative grammar was an attempt to figure out how this is done but I
think the study of the subject got a little sidetracked onto the problems
of defining a computational system of what is ‘grammatical’ rather than
what is that is to be understood.



But Hausser has given us a little more freedom to use in our attempts to
figure this problem out.

Jim


On Sun, Mar 24, 2013 at 5:00 PM, Piaget Modeler
<[email protected]>wrote:

>
>
> ------------------------------
> Date: Sun, 24 Mar 2013 10:43:26 +0100
> Subject: Re: Parsing Natural Language
> From: Roland Hausser
> To: [email protected]
>
>
> Hello Mike,
>
> Thank you for your email and the comments by
> Jim Bromer and Steve Richfield.  They touch
> on some very general issues which are difficult
> to address specifically.  Therefore I attach a
> recent paper which appeared in
>
>   Semantics in Data and Knowledge Bases: 5th International
>   Workshop SDKB 2011, Zürich, Switzerland, July 3, 2011,
>   Revised Selected Papers (LNCS 7693
>   Applications, incl. Internet/Web, and HCI) [Paperback]
>   Klaus-Dieter Schewe (Editor), Bernhard Thalheim (Editor)
>   ISBN-10: 3642360076
>   ISBN-13: 978-3642360077
>
> The editors asked for an introduction to DBS, giving
> me space.
>
> Please pass the .pdf on to those in your group who are
> interested.  Looking forward for to further reactions,
>
> Cheers,
>
> Roland
>
>



-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657
Powered by Listbox: http://www.listbox.com

Reply via email to