A Hybrid Approach For Spoken Language Machine Translation
Authors
Wenhan Chao1, Zhoujun Li, Yuexin Chen
1School of Computer Science, National University of Defense Technology, Changsha, Hunan, P.R.China
Corresponding Author
Wenhan Chao
Available Online October 2007.
- DOI
- 10.2991/iske.2007.197How to use a DOI?
- Keywords
- SMT, EBMT, Re-Ordering model
- Abstract
In this paper, we propose a hybrid approach, which is a statistical machine translation (SMT), while using an example-based decoder. In this way, it will solve efficiently the re-ordering problem in SMT and the problems for spoken language MT, such as lots of omissions, idioms etc. We present a novel re-ordering model for SMT firstly and then an example-based decoder. Through experiments, we show that this approach obtains significant improvements over the baseline on a Chinese-English spoken language translation task.
- Copyright
- © 2007, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Wenhan Chao AU - Zhoujun Li AU - Yuexin Chen PY - 2007/10 DA - 2007/10 TI - A Hybrid Approach For Spoken Language Machine Translation BT - Proceedings of the 2007 International Conference on Intelligent Systems and Knowledge Engineering (ISKE 2007) PB - Atlantis Press SP - 1154 EP - 1160 SN - 1951-6851 UR - https://doi.org/10.2991/iske.2007.197 DO - 10.2991/iske.2007.197 ID - Chao2007/10 ER -