[sidarape]

> it is better to rely on ML than on low-quality theory.

Isn't ML (and especially deep learning i.e. neural networks) itself a low-quality theory? From what I understand, nobody really knows why it works so well but uses it anyway.

[Isamu]

In this context, higher-quality == produces results == allows automatic translation with reasonable fidelity.

But I agree, it is a not a very explanitory theory since it is too black-box.