Learning Structural Kernels for Natural Language Processing
File(s)
Published version
Author(s)
Beck, Daniel
Cohn, Trevor
Hardmeier, Christian
Specia, Lucia
Type
Journal Article
Abstract
Structural kernels are a flexible learning paradigm that has been widely used in Natural Language Processing. However, the problem of model selection in kernel-based methods is usually overlooked. Previous approaches mostly rely on setting default values for kernel hyperparameters or using grid search, which is slow and coarse-grained. In contrast, Bayesian methods allow efficient model selection by maximizing the evidence on the training data through gradient-based methods. In this paper we show how to perform this in the context of structural kernels by using Gaussian Processes. Experimental results on tree kernels show that this procedure results in better prediction performance compared to hyperparameter optimization via grid search. The framework proposed in this paper can be adapted to other structures besides trees, e.g., strings and graphs, thereby extending the utility of kernel-based methods.
Date Issued
2015-08-01
Date Acceptance
2015-07-01
Citation
Transactions of the Association for Computational Linguistics, 2015, 3, pp.461-473
Publisher
Association for Computational Linguistics
Start Page
461
End Page
473
Journal / Book Title
Transactions of the Association for Computational Linguistics
Volume
3
Copyright Statement
© 2015 Association for Computational Linguistics. Distributed under a CC-BY 4.0 license (https://creativecommons.org/licenses/by/4.0/).
Identifier
http://arxiv.org/abs/1508.02131v1
Subjects
cs.CL
cs.CL
cs.LG
Notes
Transactions of the Association for Computational Linguistics, 2015
Publication Status
Published
Date Publish Online
2015-08-01