Sciweavers

Share
NAACL
2010

Improved Models of Distortion Cost for Statistical Machine Translation

8 years 10 months ago
Improved Models of Distortion Cost for Statistical Machine Translation
The distortion cost function used in Mosesstyle machine translation systems has two flaws. First, it does not estimate the future cost of known required moves, thus increasing search errors. Second, all distortion is penalized linearly, even when appropriate reorderings are performed. Because the cost function does not effectively constrain search, translation quality decreases at higher distortion limits, which are often needed when translating between languages of different typologies such as Arabic and English. To address these problems, we introduce a method for estimating future linear distortion cost, and a new discriminative distortion model that predicts word movement during translation. In combination, these extensions give a statistically significant improvement over a baseline distortion parameterization. When we triple the distortion limit, our model achieves a +2.32 BLEU average gain over Moses.
Spence Green, Michel Galley, Christopher D. Mannin
Added 14 Feb 2011
Updated 14 Feb 2011
Type Journal
Year 2010
Where NAACL
Authors Spence Green, Michel Galley, Christopher D. Manning
Comments (0)
books