Is this a Babel fish?
e.g, "Don't eat that!" "We are friendly, don't shoot" "There is food in the kitchen" "Where is the nearest bathroom?"...That will all work relatively well.
Punishing others with Vogon poetry in their own native tongue... never gonna happen.
The other factor is that complex use of natural languages depend on and require ambiguity and layered meaning and hosts of other factors that are really hard to handle.
A fairly trivial example is a pun. Translating highly idiomatic things of this nature turns out to be extraordinarily hard, and just throwing more data at a DNN is not going to get you too far down that road.
You can absolutely make a "direct" word-for-word translation of a pun in english to, say, russian. It's just not a pun any more when you're done. Often there are no "pun equivalents" with totally different words, because usually they hinge on culturally specific references that also don't translate well.
Basically none of this matters when what you're interested in is subway directions or ordering food or whatever, but it becomes intractable really fast whenever you're interested in talking about something more meaningful.
Translate words and it's gibberish. Pairs of words and you start to get slang. Triples and you can distinguish word that are different parts of speech in different contexts. Quads and grammar is mostly in the bag. 5-grams and most puns are handled. 6-grams and you've taken care of all simple sentences. Etc.
No need for semantics when n-gram counts does just as well.
With enough people talking, we'll eventually have taught Google all the translations for all possible sentences. (joking, but only halfway)
you can't do this anyway.
>No need for semantics when n-gram counts does just as well.
They don't. neither do bag of words, word2vec, or whatever.
Simple imperative language? Absolutely, this all works pretty well. Anything else? Ha.