Evaluating parsing strategies using standardized parse files

Authors:
Ralph Grishman;Catherine Macleod;John Sterling
Affiliations:
New York University, New York, New York;New York University, New York, New York;New York University, New York, New York
Venue:
ANLC '92 Proceedings of the third conference on Applied natural language processing
Year:
1992

Citing 7
Cited 13

Third message understanding evaluation and conference (MUC-3): phase 1 status report

HLT '91 Proceedings of the workshop on Speech and Natural Language
Procedure for quantitatively comparing the syntactic coverage of English grammars

HLT '91 Proceedings of the workshop on Speech and Natural Language
Statistical parsing of messages

HLT '90 Proceedings of the workshop on Speech and Natural Language
Statistical techniques for parsing messages

Statistical techniques for parsing messages
Parse fitting and prose fixing: getting a hold on ill-formedness

Computational Linguistics - Special issue on ill-formed input
A stochastic approach to sentence parsing

ACL '84 Proceedings of the 10th International Conference on Computational Linguistics and 22nd annual meeting on Association for Computational Linguistics
Information extraction and semantic constraints

COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 3

Review of "Advances in probabilistic and other parsing technologies" by Harry Bunt and Anton Nijholt. Kluwer Academic Publishers 2000.

Computational Linguistics
Review of "Industrial parsing of software manuals" by Richard F. E. Sutcliffe, Heinz-Detlev Koth, and Annette McElligott. Editions Rodopi 1996.

Computational Linguistics
Mostly-unsupervised statistical segmentation of Japanese Kanji sequences

Natural Language Engineering
Robustness beyond shallowness: incremental deep parsing

Natural Language Engineering
Mostly-unsupervised statistical segmentation of Japanese: applications to kanji

NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
Automatic extraction of subcategorization from corpora

ANLC '97 Proceedings of the fifth conference on Applied natural language processing
An empirical study on thematic knowledge acquisition based on syntactic clues and heuristics

ACL '93 Proceedings of the 31st annual meeting on Association for Computational Linguistics
Restructuring tagged corpora with morpheme adjustment rules

COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 1
Acquisition of selectional patterns

COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 2
New York University PROTEUS system: MUC-4 test results and analysis

MUC4 '92 Proceedings of the 4th conference on Message understanding
Evaluating State-of-the-Art Treebank-style Parsers for Coh-Metrix and Other Learning Technology Environments

Natural Language Engineering
Evaluating state-of-the-art treebank-style parsers for Coh-metrix and other learning technology environments

EdAppsNLP 05 Proceedings of the second workshop on Building Educational Applications Using NLP
Efficient large-scale parsing: a survey

Proceedings of the COLING-2000 Workshop on Efficiency In Large-Scale Parsing Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

The availability of large files of manually-reviewed parse trees from the University of Pennsylvania "tree bank", along with a program for comparing system-generated parses against these "standard" parses, provides a new opportunity for evaluating different parsing strategies. We discuss some of the restructuring required to the output of our parser so that it could be meaningfully compared with these standard parses. We then describe several heuristics for improving parsing accuracy and coverage, such as closest attachment of modifiers, statistical grammars, and fitted parses, and present a quantitative evaluation of the improvements obtained with each strategy.