Loading...
Loading...

Go to the content (press return)

State-of-the-art word reordering approaches in statistical machine translation: a survey

Author
Ruiz, M.; Fonollosa, José A. R.
Type of activity
Journal article
Journal
IEICE transactions on information and systems
Date of publication
2009-11-01
Volume
E92-D
Number
11
First page
2179
Last page
2185
DOI
https://doi.org/10.1587/transinf.E92.D.2179 Open in new window
Repository
http://hdl.handle.net/2117/7494 Open in new window
URL
http://search.ieice.org/bin/summary.php?id=e92-d_11_2179&category=D&year=2009&lang=E&abst= Open in new window
Abstract
This paper surveys several state-of-the-art reordering techniques employed in Statistical Machine Translation systems. Reordering is understood as the word-order redistribution of the translated words. In original SMT systems, this different order is ony modeled within the limits of translation units. Relying only in the reordering provided by translation units may not be good enought in most language pairs, whichmight require longer reorderings. Therefore, additional techniques may be deployed ...
Citation
Costa-Jussà, M. R.; Fonollosa, José A. R. State-of-the-Art word reordering approaches in statistical machine translation: a survey. "IEICE transactions on information and systems", 01 Novembre 2009, vol. E92-D, núm. 11, p. 2179-2185.
Group of research
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center
TALP - Centre for Language and Speech Technologies and Applications
VEU - Speech Processing Group

Attachments