I am working with a technical/radio technology domain. Mostly
translating manuals and technical documents. Some documents have more
conversational text which my MT module isn't translating well.
--
Taylor Rose
Machine Translation Intern
Language Intelligence
IRC: Handle: trose
Server: freenode
On Fri, 2011-09-30 at 10:21 -0400, Lane Schwartz wrote:
> How best to procede depends on what you plan on doing. What domains do
> you want your system to translate? Does a single system need to be
> able to handle multiple domains?
>
> On Fri, Sep 30, 2011 at 10:17 AM, Taylor Rose
> <[email protected]> wrote:
> > Hello,
> >
> > I'm currently working with a translation module that is trained on very
> > technical data. However, it is not producing adequate translations for
> > conversational and "general" vocabulary. My first thought is to combine
> > my training corpus with one that has a more general scope. Does anyone
> > have experience with this? Will this "water down" my technical data?
> >
> > --
> > Taylor Rose
> > Machine Translation Intern
> > Language Intelligence
> > IRC: Handle: trose
> > Server: freenode
> >
> >
> >
> > _______________________________________________
> > Moses-support mailing list
> > [email protected]
> > http://mailman.mit.edu/mailman/listinfo/moses-support
> >
>
>
>
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support
