Informatics Report Series


Report   

EDI-INF-RR-1016


Related Pages

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

Home
Title:Discriminative training of a neural network statistical parser
Authors: James Henderson
Date: 2004
Publication Title:Proc. 42nd Meeting of Association for Computational Linguistics (ACL 2004)
Publisher:Association for Computational Linguistics
Publication Type:Conference Paper Publication Status:Published
Page Nos:95-102
DOI:10.3115/1218955.1218968
Abstract:
Discriminative methods have shown significant improvements over traditional generative methods in many machine learning applications, but there has been difficulty in extending them to natural language parsing. One problem is that much of the work on discriminative methods conflates changes to the learning method with changes to the parameterization of the problem. We show how a parser can be trained with a discriminative learning method while still parameterizing the problem according to a generative probability model. We present three methods for training a neural network to estimate the probabilities for a statistical parser, one generative, one discriminative, and one where the probability model is generative but the training criteria is discriminative. The latter model outperforms the previous two, achieving state-of-the-art levels of performance (90.1% F-measure on constituents).
Links To Paper
1st Link
2nd Link
Bibtex format
@InProceedings{EDI-INF-RR-1016,
author = { James Henderson },
title = {Discriminative training of a neural network statistical parser},
book title = {Proc. 42nd Meeting of Association for Computational Linguistics (ACL 2004)},
publisher = {Association for Computational Linguistics},
year = 2004,
pages = {95-102},
doi = {10.3115/1218955.1218968},
url = {http://acl.ldc.upenn.edu/P/P04/P04-1013.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