Title: Languages as hyperplanes: Grammatical inference with string kernels
Authors: Clark, Alexander ×
Costa Florencio, Christophe
Watkins, Chris #
Issue Date: 2011
Publisher: Springer New York LLC
Series Title: Machine Learning vol:82 issue:3 pages:351-373
Abstract: Using string kernels, languages can be represented as
hyperplanes in a high dimensional feature space. We discuss the language-theoretic properties of this formalism with particular reference to the implicit feature maps defined by string kernels, considering the expressive power of the formalism, its closure properties and its relationship to other formalisms. We present a new family of grammatical inference algorithms based on this idea. We demonstrate that some mildly context-sensitive languages can be
represented in this way and that it is possible to efficiently learn these using kernel PCA. We experimentally demonstrate the effectiveness of this approach on some standard examples of context-sensitive languages using small synthetic data sets.
ISSN: 0885-6125
Publication status: published
KU Leuven publication type: IT
Appears in Collections:Informatics Section
× corresponding author
# (joint) last author

Files in This Item:
File Description Status SizeFormat
GiskLirias.pdfmain article Published 442KbAdobe PDFView/Open


All items in Lirias are protected by copyright, with all rights reserved.

© Web of science