News for hackers. Stuff that matters.

A comment on Gzip and KNN Outperforms Transformers on Text Classification. Parent comment

Re:Gzip and KNN Outperforms Transformers on Text Classification by OJFord on Thursday July 13, 2023 @08:47AM (#36708310)
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?
[ Parent | on HN ]
Re:Gzip and KNN Outperforms Transformers on Text Classification by londogard on Thursday July 13, 2023 @09:19AM (#36708671)
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.

[ Parent | on HN ]