On Fri, Oct 29, 2010 at 10:57:23PM +0100, Jimmy O'Regan wrote: > 2010/10/29 Keld Jørn Simonsen <[email protected]>: > > Hi > > > > I am not sure of the status of a way to disabling homonyms > > introduced by new entries in a monodix. An example is that I have > > about 40000 lemmas in the swedish monodix, and I would like not > > to intrude on already existing rules. I would only intrude > > the old lemmas with a new homonym, all other words should not > > make problems for existing correct translations. > > > > What is the best way to achieve this? > > Without retraining the tagger, there's no way to do that. There are > preference rules, but those only filter on tags. I think it might be > useful to extend the tagger to have a mechanism to make certain tag > choices for specific lemmas, and not too difficult to implement, based > on the existing preference rules, but it's not going to be done in a > hurry.
I don't want to exclude the new offending complete lemma, but only those surface forms of the new lemma, that gives homonyms of the old existing lemmas. This would address a concern of Jacob's about introoducing new erroneous surface forms - om my 40.000 swedish lemmas. Best regards keld ------------------------------------------------------------------------------ Nokia and AT&T present the 2010 Calling All Innovators-North America contest Create new apps & games for the Nokia N8 for consumers in U.S. and Canada $10 million total in prizes - $4M cash, 500 devices, nearly $6M in marketing Develop with Nokia Qt SDK, Web Runtime, or Java and Publish to Ovi Store http://p.sf.net/sfu/nokia-dev2dev _______________________________________________ Apertium-stuff mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/apertium-stuff
