Improving Alignment Quality in Statistical Machine Translation Using Context-Dependent Maximum Entropy Models (2002)
| Venue: | In Proc. of Coling 2002 |
| Citations: | 4 - 0 self |
BibTeX
@INPROCEEDINGS{Varea02improvingalignment,
author = {Ismael García Varea and Dpto De Informhtica and Franz J. Och and Hermann Ney and Lehrstuhl Fiir and Francisco Casacuberta},
title = {Improving Alignment Quality in Statistical Machine Translation Using Context-Dependent Maximum Entropy Models},
booktitle = {In Proc. of Coling 2002},
year = {2002},
pages = {1051--1054}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Typically, statistical alignment models are based on single-word dependencies. These models do not include contextual information, which can lead to inadequate alignments. In this paper, we present an approach to include contextual dependencies in the statistical alignment model by using a refined lexicon model. Unlike previous work, we directly integrate this in the EM algorithm of statistical alignment models. Experimental results are given for the French-English Canadian Parliament Hansards task and the Verbmobil task. The evalua- tion is performed by comparing the obtained alignments with a manually annotated reference alignment.
Citations
No citations identified.
