Sciweavers

ACL
2010

Discriminative Modeling of Extraction Sets for Machine Translation

13 years 9 months ago
Discriminative Modeling of Extraction Sets for Machine Translation
We present a discriminative model that directly predicts which set of phrasal translation rules should be extracted from a sentence pair. Our model scores extraction sets: nested collections of all the overlapping phrase pairs consistent with an underlying word alignment. Extraction set models provide two principle advantages over word-factored alignment models. First, we can incorporate features on phrase pairs, in addition to word links. Second, we can optimize for an extraction-based loss function that relates directly to the end task of generating translations. Our model gives improvements in alignment quality relative to state-of-the-art unsupervised and supervised baselines, as well
John DeNero, Dan Klein
Added 10 Feb 2011
Updated 10 Feb 2011
Type Journal
Year 2010
Where ACL
Authors John DeNero, Dan Klein
Comments (0)