Given a parallel corpus, semantic projec- tion attempts to transfer semantic role an- notations from one language to another, typically by exploiting word alignments. In this paper, we present an improved method for obtaining constituent align- ments between parallel sentences to guide the role projection task. Our extensions are twofold: (a) we model constituent alignment as minimum weight edge cov- ers in a bipartite graph, which allows us to find a globally optimal solution efficiently; (b)weproposetreepruningasapromising strategy for reducing alignment noise. Ex- perimental results on an English-German parallel corpus demonstrate improvements over state-of-the-art models.

Click Here to View the Paper In XML Format