El 2017-08-04 00:49, Hèctor Alòs i Font escribió:
2017-08-03 21:48 GMT+02:00 Francis Tyers <fty...@prompsit.com>:

El 2017-08-03 21:39, John Lyell escribió:

The bel-rus release was created with the help of: Vladislav
Kiryukhin,
Laura Janda, Francis Tyers, and John Lyell. Special thanks to
Masha
Sheyanova for her work on the Russian monolingual dictionary. In
its
current state the Belarusian to Russian performs with a coverage
of
88.2%, and the Russian to Belarusian with a coverage of 85.5% .
This
release should be used for general domain and basic language
translation for either direction. While the coverage is fairly
high,
it still needs to be improved further and tested for specific
domain
knowledge. As such, improved coverage and testing on specific
domains
remains a main focus for improving this translation pair in the
future.

Thanks John!

Note: This is the first part of John's GSOC project on bringing
bel-rus
and ukr-rus to release status. He'll now start working on ukr-rus.

Good luck!

Excellent! Congrats!

I'd like to know how much reliable is the morphological disambiguation
for Russian. This is a quite complicate issue (and, I guess, also for
bel & ukr).

The CG for Russian is described in a Nodalida paper:

URL: https://svn.code.sf.net/p/apertium/svn/branches/papers/2015-nodalida-ruscg

The rules are high recall (e.g. they rarely make the wrong choice), but a lot of
ambiguity is left unfortunately.

Fran

------------------------------------------------------------------------------
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot
_______________________________________________
Apertium-stuff mailing list
Apertium-stuff@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/apertium-stuff

Reply via email to