Comment by OJFord
2 years ago
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?
2 years ago
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?
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.