[prev in list] [next in list] [prev in thread] [next in thread] 

List:       kde-devel
Subject:    Re: Natural language processing tech for the desktop!
From:       Albert Cervera i Areny <albert () nan-tic ! com>
Date:       2008-10-25 10:25:45
Message-ID: 200810251225.45147.albert () nan-tic ! com
[Download RAW message or body]

A Dimarts 21 Octubre 2008, Jordi Polo va escriure:
>
> Any opinion about these ideas is very much welcomed.

I think an interesting application would be to process text documents (PDF, 
ODF, etc) and extract tags and information out of it to feed nepomuk. Let me 
put some examples:

Say you're a lawyer with lots of contracts of different types. You'd expect 
strigi+your application + nepomuk to recognize those contracts, put the 
appropiate tag. It also sets tags saying what kind of contract it is and even 
extracts information about the people involved. Maybe even what the contract 
is about.

For another document it might recognize it's an invoice tag it appropiately 
and set some tags such as 'invoice number', provider who sent it etc. Another 
document could be an e-book and it should guess author, title, etc.

Maybe all this might require some training or configurable (shareable) 
rules... Well just another idea.



-- 
Albert Cervera i Areny
http://www.NaN-tic.com

 
>> Visit http://mail.kde.org/mailman/listinfo/kde-devel#unsub to unsubscribe <<
[prev in list] [next in list] [prev in thread] [next in thread]