Mixing multiple translation models in statistical machine translation (2012)
| Venue: | In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics, Jeju, Republic of Korea |
| Citations: | 3 - 2 self |
BibTeX
@INPROCEEDINGS{Razmara12mixingmultiple,
author = {Majid Razmara and George Foster and Baskaran Sankaran and Anoop Sarkar},
title = {Mixing multiple translation models in statistical machine translation},
booktitle = {In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics, Jeju, Republic of Korea},
year = {2012}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Statistical machine translation is often faced with the problem of combining training data from many diverse sources into a single translation model which then has to translate sentences in a new domain. We propose a novel approach, ensemble decoding, which combines a number of translation systems dynamically at the decoding step. In this paper, we evaluate performance on a domain adaptation setting where we translate sentences from the medical domain. Our experimental results show that ensemble decoding outperforms various strong baselines including mixture models, the current state-of-the-art for domain adaptation in machine translation. 1
