This has been worked on before, yes, and is what I am looking at currently, and would be greatly interested in seeing your work.

I actually created a wiki stubb the other day with a couple of teh first papers I had seen:
 http://en.wikipedia.org/wiki/Text_simplification

Text Simplification is an important task in natural language processing, due to the fact that much of the english language is in complex compound sentences that are not easily processible for information tasks.

I believe we can translate from most simple sentences into a machine readable text., and am currently gathering a training set for converting complex sentences.

I would also like to see a comparison contrast of both of your languages, to see specific points.  Maybe you could start a wiki page on someones site.

My thoughts are though, Im afriad we almost have to stick with some form of simple english, and not require anything much stricter than that.  I think it should be able to express some levels of ambigious concepts, with maybe a interface that could ask for spcific information if it is necessary.
The system should be able to generalize, and try near concepts if they contain the answers needed.

And mainly, all the information I am using is in regular english, mostly news articles or novels, and soon to be wikipedia.

James Ratcliff

"YKY (Yan King Yin)" <[EMAIL PROTECTED]> wrote:


On 11/7/06, John Scanlon <[EMAIL PROTECTED]> wrote:
> James Ratcliff wrote:
>  
> "In some form or another we are going to HAVE to have a natural language interface, either a translation program that can convert our english to the machine  understandable form, or a simplified form of english that is trivial for a person to quickly understand and write."
>  
>  
>     This is what my language Jinnteera does.  It could be called "simplified English" but it really is its own language.  It is similar to SQL in that it is both a knowledge-base management language, with scripting capabilities, plus, most importantly, it has the expressibilty of English with a formal unambiguous parsability.  And it is easy to learn and use.  This does not solve the central AI problem, but it provides, along with the knowledge-base architecture it is designed for (similar to a database management sytem), a general AI shell, within which, any AI algorithms can be experimented with.
 
I'm working on something very similar to Jinnteera; my language is called Geniform and is half-way between English and an augmented form of predicate logic. I'd say it is closer to logic from its appearance.
 
One question is whether you can translate mechanically from English to/from your language.  I'm actually working on such a translator right now, but due to the lack of a good English parser I'm only working with simple sentences.
 
Has this been done before, and what kind of insight was gained by researchers?
 
YKY

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/?list_id=303



Thank You
James Ratcliff
http://falazar.com


Cheap Talk? Check out Yahoo! Messenger's low PC-to-Phone call rates.
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/?list_id=303

Reply via email to