Informatics Report Series


Report   

EDI-INF-RR-1014


Related Pages

Report (by Number) Index
Report (by Date) Index
Author Index
Institute Index

Home
Title:Data-defined kernels for parse reranking derived from probabilistic models
Authors: James Henderson ; Ivan Titov
Date: 2005
Publication Title:Proc. 43nd Meeting of Association for Computational Linguistics (ACL 2005)
Publisher:Association for Computational Linguistics
Publication Type:Conference Paper Publication Status:Published
Page Nos:181-188
DOI:10.3115/1219840.1219863
Abstract:
Previous research applying kernel methods to natural language parsing have focussed on proposing kernels over parse trees, which are hand-crafted based on domain knowledge and computational considerations. In this paper we propose a method for defining the kernel in terms of a probabilistic model of parsing. This model is then trained, so that the parameters of the probabilistic model reflect the generalizations in the training data. The method we propose then uses these trained parameters to define a kernel for reranking parse trees. In experiments, we use a neural network based statistical parser as the probabilistic model, and use the resulting kernel with the Voted Perceptron algorithm to rerank the top 20 parses from the probabilistic model. This method achieves a significant improvement over the accuracy of the probabilistic model alone.
Links To Paper
1st Link
Bibtex format
@InProceedings{EDI-INF-RR-1014,
author = { James Henderson and Ivan Titov },
title = {Data-defined kernels for parse reranking derived from probabilistic models},
book title = {Proc. 43nd Meeting of Association for Computational Linguistics (ACL 2005)},
publisher = {Association for Computational Linguistics},
year = 2005,
pages = {181-188},
doi = {10.3115/1219840.1219863},
url = {http://homepages.inf.ed.ac.uk/jhender6/papers/henderson_acl05.pdf},
}


Home : Publications : Report 

Please mail <reports@inf.ed.ac.uk> with any changes or corrections.
Unless explicitly stated otherwise, all material is copyright The University of Edinburgh