Do you mean how hard it is to write a compiler for it?
That's funny. I assumed you meant programming language. Off the top of my head, I'd expect if anything the opposite relationship, because the simpler the language, the more you'd depend on knowledge of the world to generate a correct translation.
-
-
For example, you'd need a very sophisticated program to translate the language consisting of just the word "dude," said with 250 different intonations.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
20y ago, with rule based translators, complex languages required more work. 10y ago statistical MT we used the same tech with extra tricks to translate morphologically complex languages. Today we use deep neural nets for all langauges and their input is the simple chars stream.
-
Complex languages still require more data.
@paulg intuition about simple and hard is also a very good one. research is working on extracting meaning also form non-text data. To summarize: “hard” is proportional to both morphological complexity and compression (simplicity).
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.