Non-local modeling with a mixture of PCFGs

Authors:
Slav Petrov;Leon Barrett;Dan Klein
Affiliations:
University of California at Berkeley, Berkeley, CA;University of California at Berkeley, Berkeley, CA;University of California at Berkeley, Berkeley, CA
Venue:
CoNLL-X '06 Proceedings of the Tenth Conference on Computational Natural Language Learning
Year:
2006

Citing 11
Cited 0

Foundations of statistical natural language processing

Foundations of statistical natural language processing
The syntactic process

The syntactic process
Improving Text Classification by Shrinkage in a Hierarchy of Classes

ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Head-driven statistical models for natural language parsing

Head-driven statistical models for natural language parsing
PCFG models of linguistic tree representations

Computational Linguistics
A maximum-entropy-inspired parser

NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
Some computational properties of Tree Adjoining Grammars

ACL '85 Proceedings of the 23rd annual meeting on Association for Computational Linguistics
A computational model of language performance: Data Oriented Parsing

COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 3
Accurate unlexicalized parsing

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Probabilistic CFG with latent annotations

ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Tree-bank grammars

AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 2

Quantified Score

Hi-index	0.00

Visualization

Abstract

While most work on parsing with PCFGs has focused on local correlations between tree configurations, we attempt to model non-local correlations using a finite mixture of PCFGs. A mixture grammar fit with the EM algorithm shows improvement over a single PCFG, both in parsing accuracy and in test data likelihood. We argue that this improvement comes from the learning of specialized grammars that capture non-local correlations.