[Wikimedia-l] Human-assisted machine translation (it was: "The case for supporting open source machine translation")

[David Cuenca]

>From what I read, Apertium also supports morphological analyzers (like:
[1], [2] and [3]). I used the term "word" because it is more approachable
for a first stage development. Later on it could be expanded to support
languages that don't use words. In any case I think it is preferable to
assist MT in form of platform and community support rather than getting
involved in research projects.

In answer to Matthieu, I don't think perfection is something to aim for
during the first stage. Just a MT that gives a fairly good text about the
subject without big mistakes, would be already a big improvement. IMHO,
goals should be set step by step and at a reasonable height. The lowest
hanging fruit seems to be pairs of closely related languages, tolerating
instances like the one you pointed out.

David


[1] http://www.ling.helsinki.fi/kieliteknologia/tutkimus/hfst/
[2] http://www.cis.uni-muenchen.de/~schmid/tools/SFST/
[3] https://code.google.com/p/foma/

On Wed, May 1, 2013 at 8:33 AM, Fred Bauder <fredbaud at fairpoint.net> wrote:

> All European languages, with the exception of Basque, are essentially one
> language with different vocabulary. MT should generally work, but needs
> help as the example shows. The big, and perhaps insurmountable, problem
> comes with trying to use it with say, Hopi, which assigns meanings in a
> wholly different way.
>
> Fred
>
> > Ha, I just met a good example of a text you may hardly translate with MT
> > means.
> >
> > Look at this text which come from [1]:
> >
> > The term "manifold" comes from German Mannigfaltigkeit, by Riemann. In
> > Romance languages, this is translated as "variety" – such spaces with a
> > differentiable structure are called "analytic varieties", while spaces
> > with an algebraic structure are called "algebraic varieties". In
> > English, "manifold" refers to spaces with a differentiable or
> > topological structure, while "variety" refers to spaces with an
> > algebraic structure, as in algebraic varieties.
> >
> > This is a good example because cleary in German you obviously won't say
> > that Mannigfaltigkeit come from the German Mannigfaltigkeit. Also if you
> > translate it to a Romance language like French you won't formulate this
> > paragraph in the same way.
> >
> > Well, it doesn't add more to what I already said, but it probably give a
> > more concrete example of MT limits.
> >
> >
> > [1] http://en.wikipedia.org/wiki/History_of_manifolds_and_varieties
> >
> > _______________________________________________
> > Wikimedia-l mailing list
> > Wikimedia-l at lists.wikimedia.org
> > Unsubscribe: https://lists.wikimedia.org/mailman/listinfo/wikimedia-l
> >
>
>
>
> _______________________________________________
> Wikimedia-l mailing list
> Wikimedia-l at lists.wikimedia.org
> Unsubscribe: https://lists.wikimedia.org/mailman/listinfo/wikimedia-l
>



-- 
Etiamsi omnes, ego non