Automatically assigned DDC number: 00635

Manually assigned DDC number: 00635

Number of references: 0

Title: On the Applicability of Neural Network and Machine Learning Methodologies to Natural Language Processing

Author:

Author:

Author:

Subject: Steve Lawrence,C. Lee Giles,Sandiway Fong On the Applicability of Neural Network and Machine Learning Methodologies to Natural Language Processing

Description: We examine the inductive inference of a complex grammar - specifically, we consider the task of training a model to classify natural language sentences as grammatical or ungrammatical, thereby exhibiting the same kind of discriminatory power provided by the Principles and Parameters linguistic framework, or Government-and-Binding theory. We investigate the following models: feed-forward neural networks, Fransconi-Gori-Soda and Back-Tsoi locally recurrent networks, Elman, Narendra & Parthasarathy, and Williams & Zipser recurrent networks, Euclidean and edit-distance nearest-neighbors, simulated annealing, and decision trees. The feed-forward neural networks and non-neural network machine learning models are included primarily for comparison. We address the question: How can a neural network, with its distributed nature and gradient descent based iterative calculations, possess linguistic capability which is traditionally handled with symbolic computation and recursive processes? Initial...

Contributor: The Pennsylvania State University CiteSeer Archives

Publisher: unknown

Date: 1995-06-26

Pubyear: 1995

Format: ps

Identifier: http://citeseer.ist.psu.edu/140951.html

Source: http://www.coling.uni-freiburg.de/~neuhaus/papers/lawrence/3479.ps.gz

Language: en

Rights: unrestricted