State-of-the-Art Word Reordering Approaches in Statistical Machine Translation: A Survey

Marta R. COSTA-JUSSA  Jose A. R. FONOLLOSA  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E92-D   No.11   pp.2179-2185
Publication Date: 2009/11/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E92.D.2179
Print ISSN: 0916-8532
Type of Manuscript: SURVEY PAPER
Category: Natural Language Processing
Keyword: 
Word Reordering,  Statistical Machine Translation,  

Full Text: PDF(257.8KB)
>>Buy this Article


Summary: 
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 only modeled within the limits of translation units. Relying only in the reordering provided by translation units may not be good enough in most language pairs, which might require longer reorderings. Therefore, additional techniques may be deployed to face the reordering challenge. The Statistical Machine Translation community has been very active recently in developing reordering techniques. This paper gives a brief survey and classification of several well-known reordering approaches.