Supertagged Phrase-based Statistical Machine Translation (2007)
Cached
Download Links
| Venue: | In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics (ACL’07 |
| Citations: | 21 - 7 self |
BibTeX
@INPROCEEDINGS{Hassan07supertaggedphrase-based,
author = {Hany Hassan and Mary Hearne and Andy Way},
title = {Supertagged Phrase-based Statistical Machine Translation},
booktitle = {In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics (ACL’07},
year = {2007},
pages = {288--295}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Phrase-based Statistical Machine Translation (PBSMT) systems represent the dominant approach in MT today. However, unlike systems in other paradigms, it has proven difficult to date to incorporate syntactic knowledge in order to improve translation quality. This paper improves on recent research which uses ‘syntactified ’ target language phrases, by incorporating supertags as constraints to better resolve parse tree fragments. In addition, we do not impose any sentence-length limit, and using a log-linear decoder, we outperform a stateof-the-art PBSMT system by over 1.3 BLEU points (or 3.51% relative) on the NIST 2003 Arabic–English test corpus. 1.
