Using a Bilingual Context in Word-Based Statistical Machine Translation

Christoph Schmidt, David Vilar, Hermann Ney

2008

Abstract

In statistical machine translation, phrase-based translation (PBT) models lead to a significantly better translation quality over single-word-based (SWB) models. PBT models translate whole phrases, thus considering the context in which a word occurs. In this work, we propose a model which further extends this context beyond phrase boundaries. The model is compared to a PBT model on the IWSLT 2007 corpus. To profit from the respective advantages of both models, we use a model combination, which results in an improvement in translation quality on the examined corpus.

Paper Citation

in Harvard Style

Schmidt C., Vilar D. and Ney H. (2008). Using a Bilingual Context in Word-Based Statistical Machine Translation . 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 144-153. DOI: 10.5220/0001742201440153

in Bibtex Style

@conference{pris08,
author={Christoph Schmidt and David Vilar and Hermann Ney},
title={Using a Bilingual Context in Word-Based Statistical Machine Translation},
booktitle={Proceedings of the 8th International Workshop on Pattern Recognition in Information Systems - Volume 1: PRIS, (ICEIS 2008)},
year={2008},
pages={144-153},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001742201440153},
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 - Using a Bilingual Context in Word-Based Statistical Machine Translation
SN - 978-989-8111-42-5
AU - Schmidt C.
AU - Vilar D.
AU - Ney H.
PY - 2008
SP - 144
EP - 153
DO - 10.5220/0001742201440153