Conference Proceedings


Qun Liu
Andy Way
Liangyou Li



source translation machine translating english german improvement segmentation search

Graph-based translation via graph segmentation (2016)

Abstract 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.
Collections Ireland -> Dublin City University -> Publication Type = Conference or Workshop Item
Ireland -> Dublin City University -> DCU Faculties and Centres = DCU Faculties and Schools: Faculty of Engineering and Computing: School of Computing
Ireland -> Dublin City University -> DCU Faculties and Centres = Research Initiatives and Centres: ADAPT
Ireland -> Dublin City University -> Status = Published
Ireland -> Dublin City University -> Subject = Computer Science: Machine translating

Full list of authors on original publication

Qun Liu, Andy Way, Liangyou Li

Experts in our system

Qun Liu
Dublin City University
Total Publications: 31
Andy Way
Dublin City University
Total Publications: 229
Liangyou Li
Dublin City University
Total Publications: 9