Re: New Machine Translation Project

Paul Bennett wrote:
>
> Ph.D. wrote:
>
> > Anyway, I thought perhaps someone here might be
> > interested.
> >
> > http://unikom.org/
>
> I love the reason they'll succeed where others have
> failed:
>
> "We'll cope with the stuff MT doesn't do well ... by ...
> uhh ... MAKING A HUMAN DO IT! Yeah, that's the
> ticket!"
Even better, is the way I found their web site. They
are currently looking to hire a HUMAN to translate
their web site into Esperanto, even though they claim
they will soon be beta-testing their English-to-Esperanto
software.


> Also, one would think that the ideal medium for an
> intermediate language would be one which is
> specifically designed for the purpose (i.e. machine-
> readable, self-segregating, and all the other things),
> as opposed to one whose goal was (more or less)
> to be readily human-learnable.
Yes, back when the European firm DLT was working
on the same sort of project, I tried to argue this to a
group of Esperantists. I suggested that the intermediate
language would not need to be human speakable at all,
but rather a tree somewhat like the sentence diagrams
we were taught back in primary school. (They would
have none of it, and insisted the the DLT project would
be the "fina venko.")


> My instinctive objections to "man in the middle" MT
> aside, I wish them the very best of luck.
Indeed.

--Ph. D.

Reply