KNESER-NEY BIGRAM SMOOTHING
- Absolute discounting involves subtracting a fixed discount, D,
from each nonzero count, an redistributing this probability mass
to N-grams with zero counts.
- We implement absolute discounting using an interpolated model:
- Kneser-Ney smoothing combines notions of discounting
with a backoff model. Here is an algorithm for bigram smoothing:
- Knesser-Ney smoothing constructs a lower order distribution that
is consistent with the smoothed higher order distribution.