Sciweavers

Share
EMNLP
2010

Discriminative Instance Weighting for Domain Adaptation in Statistical Machine Translation

9 years 1 months ago
Discriminative Instance Weighting for Domain Adaptation in Statistical Machine Translation
We describe a new approach to SMT adaptation that weights out-of-domain phrase pairs according to their relevance to the target domain, determined by both how similar to it they appear to be, and whether they belong to general language or not. This extends previous work on discriminative weighting by using a finer granularity, focusing on the properties of instances rather than corpus components, and using a simpler training procedure. We incorporate instance weighting into a mixture-model framework, and find that it yields consistent improvements over a wide range of baselines.
George F. Foster, Cyril Goutte, Roland Kuhn
Added 11 Feb 2011
Updated 11 Feb 2011
Type Journal
Year 2010
Where EMNLP
Authors George F. Foster, Cyril Goutte, Roland Kuhn
Comments (0)
books