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 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. Experiments also suggest that our model has
better capability to perform long-distance
reordering and is more suitable for translating long sentences.
This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:
People Programme (Marie Curie Actions) of the European Union’s Framework Programme (FP7/2007- 2013) under REA grant agreement no 317471, ADAPT Centre for Digital Content Technology is funded under the SFI Research Centres Programme (Grant 13/RC/2106) and is co-funded under the European Regional Development Fund.
ID Code:
23335
Deposited On:
21 May 2019 15:44 by
Thomas Murtagh
. Last Modified 22 Jul 2019 14:04