Correct Start Probabilities #2

merged 1 commit into from Apr 1, 2013


None yet

2 participants

rjhall commented Apr 1, 2013

This is a decent way to do it imho. Since this is a trigram model it makes sense to define a unique start state (which in this case is (start, start)), and then to generate from there.

@aconbere aconbere merged commit 0a2f962 into aconbere:master Apr 1, 2013
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment