Hello everyone,
It's me again, nagging about the GSOC ideas page.
We have 17 ideas, of which:
The following are perfect (nicely described, mentors + long "read more"
page):
* Bring a released language pair up to state-of-the-art quality
* Adopt an unreleased language pair
* Extend lttoolbox to have the power of HFST
* Robust recursive transfer
* Extend weighted transfer rules
* Improvements to the Apertium website
* User-friendly lexical selection training
* Light alternative format for all XML files in an Apertium language
pair
* Bilingual dictionary enrichment via graph completion
* Add weights to lttoolbox
[Note: A lot of these have been around for years]
The following need work (better "read more" page):
* Anaphora resolution for machine translation
* Robust tokenisation in lttoolbox
* UD and Apertium integration
* Unsupervised weighting of automata
* Improvements to UD Annotatrix
The following have no "read more" page:
* Eliminate dictionary trimming
* Improving language pairs mining Mediawiki Content Translation
postedits
We want to look really good for Google when they review the page, and I
think it's better to have fewer, high quality tasks than tasks which are
underspecified.
So, it would be great to get these fleshed out today, Google gave the
deadline of 19h00 today (some timezone).
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
