Paper: An SVM-Based Voting Algorithm With Application To Parse Reranking

ACL ID W03-0402
Title An SVM-Based Voting Algorithm With Application To Parse Reranking
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2003
Authors

This paper introduces a novel Support Vec- tor Machines (SVMs) based voting algorithm for reranking, which provides a way to solve the sequential models indirectly. We have presented a risk formulation under the PAC framework for this voting algorithm. We have applied this algorithm to the parse reranking problem, and achieved labeled recall and pre- cision of 89.4%/89.8% on WSJ section 23 of Penn Treebank.