On 5 April 2011 21:24, HelioH <[email protected]> wrote:
> Hello,
> my name is Helio Henrique Lopes Costa Monte Alto and I am a Computer
> Science student at Universidade Estadual de Maringá (Maringá State
> University), located in Maringá, Paraná, Brazil. I am in 4th year (the
> last year) of my course, and I do undergraduate research project. My
> research area is related to Intelligent Systems Development, with
> focus on multi-agent systems and ontologies. Currently, I’m focused on
> ontologies, which includes ontology languages, such as OWL and RDF.
>
> I’m interested in machine translation because I think it is a growing
> area and it increasingly needs to be improved. I imagine that, in a
> not too distant future, people with different native languages will
> not have trouble in communicating, thanks to translation technologies
> incorporated into personal devices. I think an open source project
> aiming at building language tools is an amazing initiative. It allows
> the software to be continually improved by the community for the
> benefit of all.
>
> I’m interested in '''Dictionary induction from wikis''', because it
> would be very useful for automatically building dictionaries for
> Apertium, and also for myself, because I’m going to be able to acquire
> more knowledge about ontology queries (RDF queries, for example).
> Therefore, it will be good for my researches on ontologies.
>

The idea is that part of the project will collect general information
in RDF, but part of it is also to convert that information into
Apertium's dictionary format.

> About my experience: apart from my research, I've worked on some
> projects from University. I think my main work until now is a software
> system for the university restaurant of my University, which includes
> inventory management, menu management and a not fully implemented yet
> (because of bureaucratic reasons with the University's policy) ticket
> selling and controlling manager (tickets for consumption in the
> restaurant, which is currently done manually). With this one, I
> acquired more experience with Java and MySQL, but I've already worked
> with C++, PHP, Python, C and Assembly. Recently, I've been exploring
> multiagents frameworks and ontology frameworks, such as JENA.
>
>
> == Questions about my application ==
>
> Basically, I will have to design and implement queries to wikis'
> databases, extract the useful information from the results and then
> build dictionaries from these informations, right? Since interpreting
> page content from wikipedia (and other sources which, I think, are not
> semantically organized) is not a trivial task (I think so), and I'd
> like to work with ontologies, I was wondering if I could work only
> with DBpedia.
>

Wikipedia is semi-structured. Categories have been mapped manually (in
DBpedia), but inferences based on those could be improved (for
example, 'Battle of Waterloo' could have the category 'Napoleon',
which would give it a type of 'Person', which is not correct).

As we're primarily interested in linguistic information, Wiktionary is
a higher priority source.

>
> I've already created an account on Apertium's wiki, my page is:
> http://wiki.apertium.org/wiki/User:Helioh2. I'm still working on my
> proposal, which is available on that page. I will try to be in IRC
> whenever possible, too. My name in IRC: helioh2.

Ok, let us know when you've done some more work on the proposal.

-- 
<Leftmost> jimregan, that's because deep inside you, you are evil.
<Leftmost> Also not-so-deep inside you.

------------------------------------------------------------------------------
Xperia(TM) PLAY
It's a major breakthrough. An authentic gaming
smartphone on the nation's most reliable network.
And it wants your games.
http://p.sf.net/sfu/verizon-sfdev
_______________________________________________
Apertium-stuff mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/apertium-stuff

Reply via email to