Wide coverage natural language processing using kernel methods and neural networks for structured data

Authors:
Sauro Menchetti;Fabrizio Costa;Paolo Frasconi;Massimiliano Pontil
Affiliations:
Department of Systems and Computer Science, Universití di Firenze, Via di S. Marta 3, 50139 Firenze, Italy;Department of Systems and Computer Science, Universití di Firenze, Via di S. Marta 3, 50139 Firenze, Italy;Department of Systems and Computer Science, Universití di Firenze, Via di S. Marta 3, 50139 Firenze, Italy;Department of Computer Science, University College London, Gower Street, London WC1E 6BT, UK
Venue:
Pattern Recognition Letters - Special issue: Artificial neural networks in pattern recognition
Year:
2005

Citing 7
Cited 2

Large Margin Classification Using the Perceptron Algorithm

Machine Learning - The Eleventh Annual Conference on computational Learning Theory
Exploiting generative models in discriminative classifiers

Proceedings of the 1998 conference on Advances in neural information processing systems II
What is the minimal set of fragments that achieves maximal parse accuracy?

ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
New ranking algorithms for parsing and tagging: kernels over discrete structures, and the voted perceptron

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Learning to order things

Journal of Artificial Intelligence Research
A general framework for adaptive processing of data structures

IEEE Transactions on Neural Networks
Ambiguity resolution analysis in incremental parsing of natural language

IEEE Transactions on Neural Networks

From Hopfield nets to recursive networks to graph machines: numerical machine learning for structured data

Theoretical Computer Science
Neural network for graphs: a contextual constructive approach

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Convolution kernels and recursive neural networks are both suitable approaches for supervised learning when the input is a discrete structure like a labeled tree or graph. We compare these techniques in two natural language problems. In both problems, the learning task consists in choosing the best alternative tree in a set of candidates. We report about an empirical evaluation between the two methods on a large corpus of parsed sentences and speculate on the role played by the representation and the loss function.