Re: Universal Translation Language

Tem Tue, 1 Jun 1999 22:26:39 -0500, Carlos Thompson
<carlos_thompson@...> skribis:

Hi, Carlos

>Well.  If I understand Marcos properly the sequence would be:
> 1) Software converts surce into UTL
> 2) Human make exhaustive revision of UTL (by far easier for a human =
than
>UNL)
> 3) Software translate from UTL to multiple target languages.
> 4) Human revision of style.
Well, that's a possibility, though what I have in mind is:
1) Man converts source into UTL (or even writes source directly into
UTL).
2) Software translate from UTL to multiple target languages.
3) Human revision of style.

It would be possible to develop a rough NL -> UTL machine, but it
probably wouldn't be more helpful for the human translator than NL ->
NL machine translations are for current human translators.=20

>or UTL).
>
>There are then two problems to solve: create a good UTL which is human =
and
>machine parceable,=20
That's what I'm on :)

>and create good NL->UTL and UTL->NL translators, this
>last is suposed to be much easier than any NL->NL translator and the =
NL->UTL
>doesn't need to be better than any of today's NL->NL translators.
Indeed, and even it wouldn't be (as I've explained) necessary at all
for the translation process.

What I'm now trying to find out (please somebody help me with any
information) is whether it's possible to use an already made NL
generator (that's the software which takes a parsing output and by
means of a lexical database converts it into that NL) to link it to a
(future) UNL parser&database.=20


Saludos,
Marcos