Machine translation

Machine translation is a difficult thing. It is hard to get it right, the English language Wikipedia has a problem with writing a good article about it. Some people think that with WiktionaryZ we are in the business of machine translation, as a result the subject gets on our radar screen every now and then. It would be a good characterization to say that the Machine Translation we could use is the one that is able to translate the definitions of a DefinedMeaning in all languages. This resulting translation should be good enough so that people have an idea what is meant .. in Bambara, or Papiamento... Translations like these are what we need and there are as far as I am aware no Machine Translation engines.

To create a Machine Translation engine for these language, you would need all kinds of rules about the languages that you want to translate to. Now I would like to know these rules. Not so much to build Machine Translation engines but because they have this other application, one that is much closer to my heart, it is needed for software that teaches people languages. The Universität Bamberg is working on exactly this. They want to use the data of WiktionaryZ for this purpose. So if you have a nice sets of rules for them I would be obliged.

Thanks,
GerardM