One major drawback of phrase-based
translation is that it segments an input sentence into continuous phrases. To support linguistically informed source discontinuity, in this paper we construct graphs
which combine bigram and dependency
relations and propose a graph-based translation model. The model segments an
input graph into connected subgraphs,
each of which may cover a discontinuous
phrase. We use beam search to combine
translations of each subgraph left-to-right
to produce a complete translation. Experiments on Chinese–English and German–
English tasks show that our system is
significantly better than the phrase-based
model by up to +1.5/+0.5 BLEU scores.
By explicitly modeling the graph segmentation, our system obtains further improvement, especially on German–English.
Erk, Katrin and Smith, Noah A., (eds.)
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics: Long Papers).
1.
Association for Computational Linguistics.
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, European Union’s Horizon 2020 research and innovation programme under grant agreement n o 645452 (QT21)., 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:
23346
Deposited On:
22 May 2019 14:01 by
Thomas Murtagh
. Last Modified 22 May 2019 14:01