[OJFord]

How do they work then that semantic similarity would be any different? That's just a matter of grouping semantically similar 'representations' in training, surely?

[londogard]

Yes, what I'm saying is that gzip does not perform as well when it's not overlapping tokens exact.

Gzip does not support a "semantic" mode, hence it won't and does not (according to the papers metric) perform as well.

Deep learning can capture these semantic similarities.