Informatics Report Series


Report   

EDI-INF-RR-1017


Related Pages

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

Home
Title:Inducing History Representations for Broad Coverage Statistical Parsing
Authors: James Henderson
Date: 2003
Publication Title:Proceedings of the joint meeting of the North American Chapter of the Association for Computational Linguistics and the Human Language Technology Conference
Publisher:Association for Computational Linguistics
Publication Type:Conference Paper Publication Status:Published
Page Nos:103-110
DOI:10.3115/1073445.1073459
Abstract:
We present a neural network method for inducing representations of parse histories and using these history representations to estimate the probabilities needed by a statistical left-corner parser. The resulting statistical parser achieves performance (89.1% F-measure) on the Penn Treebank which is only 0.6% below the best current parser for this task, despite using a smaller vocabulary size and less prior linguistic knowledge. Crucial to this success is the use of structurally determined soft biases in inducing the representation of the parse history, and no use of hard independence assumptions.
Links To Paper
1st Link
2nd Link
Bibtex format
@InProceedings{EDI-INF-RR-1017,
author = { James Henderson },
title = {Inducing History Representations for Broad Coverage Statistical Parsing},
book title = {Proceedings of the joint meeting of the North American Chapter of the Association for Computational Linguistics and the Human Language Technology Conference},
publisher = {Association for Computational Linguistics},
year = 2003,
pages = {103-110},
doi = {10.3115/1073445.1073459},
url = {http://acl.ldc.upenn.edu/N/N03/N03-1014.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