Paper: A Discriminative Model For Tree-To-Tree Translation

ACL ID W06-1628
Title A Discriminative Model For Tree-To-Tree Translation
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2006

This paper proposes a statistical, tree- to-tree model for producing translations. Two main contributions are as follows: (1) a method for the extraction of syn- tactic structures with alignment informa- tion from a parallel corpus of translations, and (2) use of a discriminative, feature- based model for prediction of these target- language syntactic structures—which we call aligned extended projections, or AEPs. An evaluation of the method on translation from German to English shows similar performance to the phrase-based model of Koehn et al.