Word alignment methods can gain valu- able guidance by ensuring that their align- ments maintain cohesion with respect to the phrases specified by a monolingual de- pendency tree. However, this hard con- straint can also rule out correct alignments, and its utility decreases as alignment mod- els become more complex. We use a pub- licly available structured output SVM to create a max-margin syntactic aligner with a soft cohesion constraint. The resulting aligner is the first, to our knowledge, to use a discriminative learning method to train an ITG bitext parser.

Click Here to View the Paper In XML Format