Dependency Graph-to-String Translation

Liangyou Li, Andy Way, Qun Liu
2015 Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing  
Compared to tree grammars, graph grammars have stronger generative capacity over structures. Based on an edge replacement grammar, in this paper we propose to use a synchronous graph-to-string grammar for statistical machine translation. The graph we use is directly converted from a dependency tree by labelling edges. We build our translation model in the log-linear framework with standard features. Large-scale experiments on Chinese-English and German-English tasks show that our model is
more » ... icantly 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. Experiments also suggest that our model has better capability to perform long-distance reordering and is more suitable for translating long sentences.
doi:10.18653/v1/d15-1004 dblp:conf/emnlp/LiWL15 fatcat:474upobprre57fxon6sbiz6pia