> (1) we could have "reduced" pairs by removing unusual (infrequent)
> vocabulary, yes. Would you like to work on a method to do so? Where would
> you get frequencies from?
>
Let's see: Apertium's language packs take about 5MB while Google
Translate's language packs take about 150MB. Do we need to make our packs
even smaller? It would be nice, of course, but I think that they are small
enough as they are (even the cheapest device has 8GB nowadays, so 5MB is
not a big deal). And in case somebody wants to work on it, the easiest way
would be to create Android specific packs rather than removing unusual
vocabulary. I mean, current packs are not only compatible with the Android
app, but also with Apertium-Caffeine, Apertium-OmegaT and they can even
work as standalone desktop applications; removing the extra stuff that is
bundled to support all this is really simple and can save some considerable
space. But I insist that, in my opinion, this would be pretty irrelevant
for 99.99% of users.
As for Google Translate's app integrating better in Android, it is true
that it has some great features that Apertium's app misses. Implementing
some of them (like offline OCR[1], which was suggested during last GSoC)
would be nice and relatively easy, but some others (like TTS or voice
recognition, at least for all the minor languages that Apertium supports)
would probably be unachievable for us. In any case, the current app is
really good as it is in my opinion, and I would say that Google's main
advantage is not the app itself but rather these two points (sorry if I'm
stating the obvious):
1) Support for "big" languages: there is surely more people interested in a
Spanish-German translator than in a Spanish-Asturian translator, for
example.
2) Marketing: Practically everybody knows about Google Translate, but not
many people do about Apertium and even less know that it has an Android app.
The first point might be a disadvantage when it comes to reach the general
public, but the focus on minor languages is, at the same time, what makes
Apertium so great. As for the second point, it's obvious that we cannot
beat Google in terms of marketing, but I personally think that we could
-and should- do something more to promote our app. We could, for instance,
contact specialized online media. For example, Weblogssl's publications
(such as xatakandroid.com) are followed by many people here and they often
write about topics -and apps- suggested by readers. Wouldn't it be nice to
suggest them to write an article about Apertium's app? It's just an idea,
perhaps somebody has already tried something like that...
[1] https://github.com/rmtheis/android-ocr
------------------------------------------------------------------------------
Minimize network downtime and maximize team effectiveness.
Reduce network management and security costs.Learn how to hire
the most talented Cisco Certified professionals. Visit the
Employer Resources Portal
http://www.cisco.com/web/learning/employer_resources/index.html
_______________________________________________
Apertium-stuff mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/apertium-stuff
