Automatic phrase alignment. Using statistical n-gram alignment for syntactic phrase alignment
Yvonne Samuelsson, Martin Volk · Zurich Open Repository and Archive (University of Zurich) · 2007
A parallel treebank consists of syntactically annotated sentences in two or more languages, taken from translated documents. These parallel sentences are linked through alignment. This paper explores the use of word n-gram alignment, computed for statistical machine translation, to create syntactic phrase alignment. We achieve a weighted F0.5 -score of over 65%.