Statistical translation alignment with compositionality constraints

Authors:
Michel Simard;Philippe Langlais
Affiliations:
Université de Montréal, Montréal (Québec), Canada;Université de Montréal, Montréal (Québec), Canada
Venue:
HLT-NAACL-PARALLEL '03 Proceedings of the HLT-NAACL 2003 Workshop on Building and using parallel texts: data driven machine translation and beyond - Volume 3
Year:
2003

Citing 4
Cited 4

A statistical approach to machine translation

Computational Linguistics
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
Improved statistical alignment models

ACL '00 Proceedings of the 38th Annual Meeting on Association for Computational Linguistics

Constrained EM for parallel text alignment

Natural Language Engineering
An evaluation exercise for word alignment

HLT-NAACL-PARALLEL '03 Proceedings of the HLT-NAACL 2003 Workshop on Building and using parallel texts: data driven machine translation and beyond - Volume 3
Aligning words using matrix factorisation

ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Partitioning parallel documents using binary segmentation

StatMT '06 Proceedings of the Workshop on Statistical Machine Translation

Quantified Score

Hi-index	0.00

Visualization

Abstract

This article presents a method for aligning words between translations, that imposes a compositionality constraint on alignments produced with statistical translation models. Experiments conducted within the WPT-03 shared task on word alignment demonstrate the effectiveness of the proposed approach.