Dependency Graph-to-String Translation

Compared to tree grammars, graph gram-mars have stronger generative capacity over structures. Based on an edge re-placement grammar, in this paper we pro-pose to use a synchronous graph-to-string grammar for statistical machine transla-tion. The graph we use is directly con-verted from a dependency tree by labelling edges. We build our translation model in the log-linear framework with stan-dard features. Large-scale experiments on Chinese–English and German–English tasks show that our model is significantly better than the state-of-the-art hierarchical phrase-based (HPB) model and a recently improved dependency tree-to-string model on BLEU, METEOR and TER scores. Ex-periments also suggest that our model has better capability to perform long-distance reordering and is more suitable for trans-lating long sentences.