Ohmm is a library for learning hidden Markov models by using Online EM algorithm. Online EM is proposed by Percy Liang.
This is specialized for NLP task, where input are redundant, very sparse, and very large. Online EM can converge about 10 times faster than traditional EM algorithm.
- Changes to previous version:
Initial Announcement on mloss.org.
No one has posted any comments yet. Perhaps you'd like to be the first?
Leave a comment
You must be logged in to post comments.