Maximum entropy model learning of the translation rules

Authors:
Kengo Sato;Masakazu Nakanishi
Affiliations:
Keio University, Yokohama, Japan;Keio University, Yokohama, Japan
Venue:
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
Year:
1998

Citing 5
Cited 2

A maximum entropy approach to natural language processing

Computational Linguistics
Inducing Features of Random Fields

Inducing Features of Random Fields
Text-translation alignment

Computational Linguistics - Special issue on using large corpora: I
A maximum entropy approach to identifying sentence boundaries

ANLC '97 Proceedings of the fifth conference on Applied natural language processing
Extracting word correspondences from bilingual corpora based on word co-occurrences information

COLING '96 Proceedings of the 16th conference on Computational linguistics - Volume 1

Structural feature selection for English-Korean statistical machine translation

COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 1
Extracting word sequence correspondences with support vector machines

COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a learning method of translation rules from parallel corpora. This method applies the maximum entropy principle to a probabilistic model of translation rules. First, we define feature functions which express statistical properties of this model. Next, in order to optimize the model, the system iterates following steps: (1) selects a feature function which maximizes loglikelihood, and (2) adds this function to the model incrementally. As computational cost associated with this model is too expensive, we propose several methods to suppress the overhead in order to realize the system. The result shows that it attained 69.54% recall rate.