I don’t see why it can’t be done without major errors. My understanding is that they give the same text to be translated to a large number of users and then use an algorithm to find the most probable translation. Whether there are “major errors” will depend on how well it is implemented.
I don’t see why it can’t be done without major errors. My understanding is that they give the same text to be translated to a large number of users and then use an algorithm to find the most probable translation. Whether there are “major errors” will depend on how well it is implemented.