Large-scale discriminative n-gram language models for statistical machine translation (2008)
| Venue: | In Proceedings of AMTA |
| Citations: | 7 - 3 self |
BibTeX
@INPROCEEDINGS{Li08large-scalediscriminative,
author = {Zhifei Li and Sanjeev Khudanpur},
title = {Large-scale discriminative n-gram language models for statistical machine translation},
booktitle = {In Proceedings of AMTA},
year = {2008}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
We extend discriminative n-gram language modeling techniques originally proposed for automatic speech recognition to a statistical machine translation task. In this context, we propose a novel data selection method that leads to good models using a fraction of the training data. We carry out systematic experiments on several benchmark tests for Chinese to English translation using a hierarchical phrase-based machine translation system, and show that a discriminative language model significantly improves upon a state-of-the-art baseline. The experiments also highlight the benefits of our data selection method. 1
