Grammar Specialization through Entropy Thresholds

Details Grammar Specialization through Entropy Thresholds Grammar Specialization through Entropy Thresholds

1994-05-25

arxiv.org/abs/cmp-lg/9405022v1

In Proceedings of ACL-94

Computer Science

Computation and Language

8 pages

Scientific paper

Explanation-based generalization is used to extract a specialized grammar from the original one using a training corpus of parse trees. This allows very much faster parsing and gives a lower error rate, at the price of a small loss in coverage. Previously, it has been necessary to specify the tree-cutting criteria (or operationality criteria) manually; here they are derived automatically from the training set and the desired coverage of the specialized grammar. This is done by assigning an entropy value to each node in the parse trees and cutting in the nodes with sufficiently high entropy values.

Affiliated with

Also associated with

No associations

Rating

Grammar Specialization through Entropy Thresholds 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 Grammar Specialization through Entropy Thresholds, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Grammar Specialization through Entropy Thresholds will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-566302