Large-scale Discriminative n-gram Language Models for Statistical Machine Translation

Zhifei Li, Sanjeev Khudanpur


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.
Anthology ID:
2008.amta-papers.12
Volume:
Proceedings of the 8th Conference of the Association for Machine Translation in the Americas: Research Papers
Month:
October 21-25
Year:
2008
Address:
Waikiki, USA
Venue:
AMTA
SIG:
Publisher:
Association for Machine Translation in the Americas
Note:
Pages:
133–142
Language:
URL:
https://aclanthology.org/2008.amta-papers.12
DOI:
Bibkey:
Cite (ACL):
Zhifei Li and Sanjeev Khudanpur. 2008. Large-scale Discriminative n-gram Language Models for Statistical Machine Translation. In Proceedings of the 8th Conference of the Association for Machine Translation in the Americas: Research Papers, pages 133–142, Waikiki, USA. Association for Machine Translation in the Americas.
Cite (Informal):
Large-scale Discriminative n-gram Language Models for Statistical Machine Translation (Li & Khudanpur, AMTA 2008)
Copy Citation:
PDF:
https://aclanthology.org/2008.amta-papers.12.pdf