A structured language model for incremental tree-to-string translation

Tree-to-string systems have gained significant popularity thanks to their simplicity and efficiency by exploring the source syntax information, but they lack in the target syntax to guarantee the grammaticality of the output. Instead of using complex tree-to-tree models, we integrate a structured language model, a left-to-right shift-reduce parser in specific, into an incremental tree-to-string model, and introduce an efficient grouping and pruning mechanism for this integration. Large-scale experiments on various Chinese-English test sets show that with a reasonable speed our method gains an average improvement of 0.7 points in terms of (Ter-Bleu)/2 than a state-of-the-art tree-to-string system.