Improving statistical word alignment with ensemble methods

Authors:
Hua Wu;Haifeng Wang
Affiliations:
Toshiba (China) Research and Development Center, Beijing, China;Toshiba (China) Research and Development Center, Beijing, China
Venue:
IJCNLP'05 Proceedings of the Second international joint conference on Natural Language Processing
Year:
2005

Citing 11
Cited 1

Bagging predictors

Machine Learning
Translating collocations for bilingual lexicons: a statistical approach

Computational Linguistics
Review Article: Example-based Machine Translation

Machine Translation
Ensemble Methods in Machine Learning

MCS '00 Proceedings of the First International Workshop on Multiple Classifier Systems
The mathematics of statistical machine translation: parameter estimation

Computational Linguistics - Special issue on using large corpora: II
Stochastic inversion transduction grammars and bilingual parsing of parallel corpora

Computational Linguistics
A simple hybrid aligner for generating lexical correspondences in parallel texts

COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
A probability model to improve word alignment

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Improved statistical alignment models

ACL '00 Proceedings of the 38th Annual Meeting on Association for Computational Linguistics
A best-first alignment algorithm for automatic extraction of transfer mappings from bilingual corpora

DMMT '01 Proceedings of the workshop on Data-driven methods in machine translation - Volume 14
Symmetric word alignments for statistical machine translation

COLING '04 Proceedings of the 20th international conference on Computational Linguistics

Exploiting discourse information to identify paraphrases

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes an approach to improve statistical word alignment with ensemble methods. Two ensemble methods are investigated: bagging and cross-validation committees. On these two methods, both weighted voting and unweighted voting are compared under the word alignment task. In addition, we analyze the effect of different sizes of training sets on the bagging method. Experimental results indicate that both bagging and cross-validation committees improve the word alignment results regardless of weighted voting or unweighted voting. Weighted voting performs consistently better than unweighted voting on different sizes of training sets.