The only difference is we don't use rANS (which didn't exist when we started), we use a different arithmetic coding technique that does not require divisions, that also handles probabilities that don't sum to a power of two, so even the traditional frequency count style of models work fine.
Glad to see others are recognizing that this is a good idea.
The only difference is we don't use rANS (which didn't exist when we started), we use a different arithmetic coding technique that does not require divisions, that also handles probabilities that don't sum to a power of two, so even the traditional frequency count style of models work fine.
Glad to see others are recognizing that this is a good idea.