Optimization of Log-linear Machine Translation Model Parameters Using SVMs

Jesús González-Rubio, Daniel Ortiz-Martínez, Francisco Casacuberta

2008

Abstract

The state-of-the art in statistical machine translation is based on a log-linear combination of different models. In this approach, the coefficients of the combination are computed by using the MERT algorithm with a validation data set. This algorithm presents high computational costs. As an alternative, we propose a novel technique based on Support Vector Machines to calculate these coefficients using a loss function to be minimized. We report the experiments on a Italian-English translation task showing encouraging results.

Download


Paper Citation


in Harvard Style

González-Rubio J., Ortiz-Martínez D. and Casacuberta F. (2008). Optimization of Log-linear Machine Translation Model Parameters Using SVMs . In Proceedings of the 8th International Workshop on Pattern Recognition in Information Systems - Volume 1: PRIS, (ICEIS 2008) ISBN 978-989-8111-42-5, pages 48-56. DOI: 10.5220/0001739000480056


in Bibtex Style

@conference{pris08,
author={Jesús González-Rubio and Daniel Ortiz-Martínez and Francisco Casacuberta},
title={Optimization of Log-linear Machine Translation Model Parameters Using SVMs},
booktitle={Proceedings of the 8th International Workshop on Pattern Recognition in Information Systems - Volume 1: PRIS, (ICEIS 2008)},
year={2008},
pages={48-56},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001739000480056},
isbn={978-989-8111-42-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 8th International Workshop on Pattern Recognition in Information Systems - Volume 1: PRIS, (ICEIS 2008)
TI - Optimization of Log-linear Machine Translation Model Parameters Using SVMs
SN - 978-989-8111-42-5
AU - González-Rubio J.
AU - Ortiz-Martínez D.
AU - Casacuberta F.
PY - 2008
SP - 48
EP - 56
DO - 10.5220/0001739000480056