Computer Science – Computation and Language
Scientific paper
1994-05-10
In Proceedings of ACL-94
Computer Science
Computation and Language
12 pages, to appear in ACL-94
Scientific paper
We present an algorithm for computing n-gram probabilities from stochastic context-free grammars, a procedure that can alleviate some of the standard problems associated with n-grams (estimation from sparse data, lack of linguistic structure, among others). The method operates via the computation of substring expectations, which in turn is accomplished by solving systems of linear equations derived from the grammar. We discuss efficient implementation of the algorithm and report our practical experience with it.
Segal Jonathan
Stolcke Andreas
No associations
LandOfFree
Precise n-gram Probabilities from Stochastic Context-free Grammars does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Precise n-gram Probabilities from Stochastic Context-free Grammars, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Precise n-gram Probabilities from Stochastic Context-free Grammars will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-288992