Using shallow syntax information to improve word alignment and reordering for SMT
Josep Crego, Nizar Y. Habash · 2008
We describe two methods to improve SMT accuracy using shallow syntax information. First, we use chunks to refine the set of word alignments typically used as a starting point in SMT systems. Second, we extend an N-gram-based SMT system with chunk tags to better account for long-distance reorderings. Experiments are reported on an Arabic-English task showing significant improvements. A human error analysis indicates that long-distance reorderings are captured effectively.