Automatic compensation for parser figure-of-merit flaws

Authors:
Don Blaheta;Eugene Charniak
Affiliations:
Brown University, Providence, RI;Brown University, Providence, RI
Venue:
ACL '99 Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics
Year:
1999

Citing 8
Cited 6

Algorithm schemata and data structures in syntactic processing

Readings in natural language processing
Statistical agenda parsing

HLT '91 Proceedings of the workshop on Speech and Natural Language
Parsing the voyager domain using pearl

HLT '91 Proceedings of the workshop on Speech and Natural Language
Calculating the probability of a partial parse of a sentence

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
New figures of merit for best-first probabilistic chart parsing

Computational Linguistics
Automatic grammar acquisition

HLT '94 Proceedings of the workshop on Human Language Technology
Statistical parsing with a context-free grammar and word statistics

AAAI'97/IAAI'97 Proceedings of the fourteenth national conference on artificial intelligence and ninth conference on Innovative applications of artificial intelligence

Attention shifting for parsing speech

ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Probabilistic context-free grammar induction based on structural zeros

HLT-NAACL '06 Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics
Stochastic Parsing and Evolutionary Algorithms

Applied Artificial Intelligence
Linear complexity context-free parsing pipelines via chart constraints

NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Time as a measure of parsing efficiency

Proceedings of the COLING-2000 Workshop on Efficiency In Large-Scale Parsing Systems
Measuring efficiency in high-accuracy, broad-coverage statistical parsing

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

Quantified Score

Hi-index	0.00

Visualization

Abstract

Best-first chart parsing utilises a figure of merit (FOM) to efficiently guide a parse by first attending to those edges judged better. In the past it has usually been static; this paper will show that with some extra information, a parser can compensate for FOM flaws which otherwise slow it down. Our results are faster than the prior best by a factor of 2.5; and the speedup is won with no significant decrease in parser accuracy.