Estimation of consistent probabilistic context-free grammars

Authors:
Mark-Jan Nederhof;Giorgio Satta
Affiliations:
Max Planck Institute for Psycholinguistics, Nijmegen, The Netherlands;University of Padua, via Gradenigo, Padova, Italy
Venue:
HLT-NAACL '06 Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics
Year:
2006

Citing 10
Cited 3

Consistency of Stochastic Context-Free Grammars From Probabilistic Estimation Based on Growth Transformations

IEEE Transactions on Pattern Analysis and Machine Intelligence
Probabilistic Languages: A Review and Some Open Questions

ACM Computing Surveys (CSUR)
Statistical Language Learning

Statistical Language Learning
Estimation of probabilistic context-free grammars

Computational Linguistics
Statistical properties of probabilistic context-free grammars

Computational Linguistics
Conditions on consistency of probabilistic Tree Adjoining Grammars

COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
Stochastic lexicalized tree-adjoining grammars

COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 2
Relating probabilistic grammars and automata

ACL '99 Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics
Introduction to Automata Theory, Languages, and Computation (3rd Edition)

Introduction to Automata Theory, Languages, and Computation (3rd Edition)
Cross-entropy and estimation of probabilistic context-free grammars

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

Maximum likelihood analysis of algorithms and data structures

Theoretical Computer Science
Reducing the size of the representation for the uDOP-estimate

EMNLP '11 Proceedings of the First Workshop on Unsupervised Learning in NLP
Stochastic context-free grammars, regular languages, and newton's method

ICALP'13 Proceedings of the 40th international conference on Automata, Languages, and Programming - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

We consider several empirical estimators for probabilistic context-free grammars, and show that the estimated grammars have the so-called consistency property, under the most general conditions. Our estimators include the widely applied expectation maximization method, used to estimate probabilistic context-free grammars on the basis of unannotated corpora. This solves a problem left open in the literature, since for this method the consistency property has been shown only under restrictive assumptions on the rules of the source grammar.