On 25 March 2011 11:36, Antonio Toral <[email protected]> wrote: > hi Sagie, > >> One thing I thought about was the "Dictionary induction from wikis" >> idea. >> I was wondering who I can talk to to get a better picture of what work >> is required for this task. > > Jimmy O'Regan (for DBPedia) and me are the folks interested in this. > > there's some work on adding Named Entities extracted from Wikipedia to > Apertium dictionaries: > http://openaccess.uoc.edu/webapps/o2/bitstream/10609/5644/3/Toral_Freerbmt11_Automatic.pdf > > and I did also some very basic multilingual dictionary extraction (just > equivalent lemmas, no added morphological info) from Wikipedia and > Wiktionary. Rudimentary as it is, it might be useful as a starting point > to build upon. > >> And also, is there a specific reason Java and Scala are listed as >> requirements for this? > > mmm, I guess that's specific for DBPedia so Jimmy might give you a > sensible answer :)
That's pretty much it. I'm really not interested in seeing yet another custom wikimedia scraper, but I am interested in seeing the DBPedia framework extended to more languages/wiktionary phenomena (it currently only supports the German wiktionary, and much of that support is hardwired). The DBPedia extraction framework is quite robust (custom scrapers tend to be quite brittle), and it has a very flexible mechanism for template extraction (see http://mappings.dbpedia.org/index.php/Main_Page). -- <Leftmost> jimregan, that's because deep inside you, you are evil. <Leftmost> Also not-so-deep inside you. ------------------------------------------------------------------------------ Enable your software for Intel(R) Active Management Technology to meet the growing manageability and security demands of your customers. Businesses are taking advantage of Intel(R) vPro (TM) technology - will your software be a part of the solution? Download the Intel(R) Manageability Checker today! http://p.sf.net/sfu/intel-dev2devmar _______________________________________________ Apertium-stuff mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/apertium-stuff
