Re:Telefunken Datenspeicher
by derefr on Sunday March 17, 2024 @03:45PM
(#39737388)
I honestly find it bizarre that this isn't one of the problems we instantly solved with LLMs.
Can't we "just" train a model with a big corpus of English, a big corpus of German, and a big corpus of human-translated Rosetta-Stone-like "annotated with translation" texts — and out will pop a "bilingual" language model that can do translation as fluently as a human could?
Do we just not have the right training data available to make this happen?
Can't we "just" train a model with a big corpus of English, a big corpus of German, and a big corpus of human-translated Rosetta-Stone-like "annotated with translation" texts — and out will pop a "bilingual" language model that can do translation as fluently as a human could?
Do we just not have the right training data available to make this happen?