Comparing Representations of Semantic Roles for String-To-Tree Decoding

We introduce new features for incorporating semantic predicate-argument structures in machine translation (MT). The methods focus on the completeness of the semantic structures of the translations, as well as the order of the translated semantic roles. We experiment with translation rules which contain the core arguments for the predicates in the source side of a MT system, and observe that using these rules significantly improves the translation quality. We also present a new semantic feature that resembles a language model. Our results show that the language model feature can also significantly improve MT results.