A 2014-06-14 10:14, Mikel Forcada escrigué:
> Dear all:
>
> I see two possibilities:
> (1) considering the Apertium project as "industrial practice" for these
> students
> (2) checking if one of the Apertium-based companies ("industries") is
> interested in having these students.
>
> I find (1) very interesting to advance any Russian-related project in
> Apertium but I wonder if it would meet the criteria. In any case, it
> could get the endorsement of Francis Tyers department in Tromsø as they
> are doing Russian linguistic technologies.
>
> What do you folks think? We should send an answer to Anastasia Bonch..
>
> All the best...
>
> Mikel
I think that (2) would be ideal, but given the short time frame we may
have to go with (1). It could be that they require some kind of
incorporated company for it to count as "industrial". That would pretty
much leave Prompsit as one of the main contenders.
Things that they could do:
1) Tag Russian corpora.
2) Develop and expand transfer lexicons for Russian--{Languages of
Russia}
3) Find and align free parallel corpora and run experiments on SMT for
Russian--{Languages of Russia}
4) Finish the Ukrainian--Russian language pair
5) Make a morphological analyser for Belarusian.
Those are five things off the top of my head. I'm sure apertiumers can
come up with more ideas :)
F.
------------------------------------------------------------------------------
HPCC Systems Open Source Big Data Platform from LexisNexis Risk Solutions
Find What Matters Most in Your Big Data with HPCC Systems
Open Source. Fast. Scalable. Simple. Ideal for Dirty Data.
Leverages Graph Analysis for Fast Processing & Easy Data Exploration
http://p.sf.net/sfu/hpccsystems
_______________________________________________
Apertium-stuff mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/apertium-stuff
