Computer Science – Computation and Language
Scientific paper
2001-05-07
Computer Science
Computation and Language
8 pages, Proceedings of the ACL 2001
Scientific paper
This paper compares two different ways of estimating statistical language models. Many statistical NLP tagging and parsing models are estimated by maximizing the (joint) likelihood of the fully-observed training data. However, since these applications only require the conditional probability distributions, these distributions can in principle be learnt by maximizing the conditional likelihood of the training data. Perhaps somewhat surprisingly, models estimated by maximizing the joint were superior to models estimated by maximizing the conditional, even though some of the latter models intuitively had access to ``more information''.
No associations
LandOfFree
Joint and conditional estimation of tagging and parsing models 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 Joint and conditional estimation of tagging and parsing models, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Joint and conditional estimation of tagging and parsing models will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-558726