Statistical machine translation model based on a synchronous tree-substitution grammar

Hong Fei Jiang; Sheng Li; Guo Hong Fu; Tie Jun Zhao; Min Zhang

doi:10.3724/SP.J.1001.2009.03409

Statistical machine translation model based on a synchronous tree-substitution grammar

Hong Fei Jiang^*
, Sheng Li
, Guo Hong Fu
, Tie Jun Zhao
, Min Zhang

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

A translation model based on synchronous tree-substitution-grammar is presented in this paper. It can elegantly model the global reordering and discontinuous phrases. Furthermore, it can learn non-isomorphic tree-to-tree mappings. Experimental results on two different data sets show that the proposed model significantly outperforms the phrase-based model and the model based on synchronous context-free grammar.

Original language	English
Pages (from-to)	1241-1253
Number of pages	13
Journal	Ruan Jian Xue Bao/Journal of Software
Volume	20
Issue number	5
DOIs	https://doi.org/10.3724/SP.J.1001.2009.03409
State	Published - May 2009
Externally published	Yes

Keywords

Global reordering
Machine translation
Non-isomorphic tree-to-tree mapping
Synchronous tree-substitution-grammar
Tree-to-tree model

Access to Document

10.3724/SP.J.1001.2009.03409

Cite this

@article{6c7395279e8145c8a402feb75b755eab,

title = "Statistical machine translation model based on a synchronous tree-substitution grammar",

abstract = "A translation model based on synchronous tree-substitution-grammar is presented in this paper. It can elegantly model the global reordering and discontinuous phrases. Furthermore, it can learn non-isomorphic tree-to-tree mappings. Experimental results on two different data sets show that the proposed model significantly outperforms the phrase-based model and the model based on synchronous context-free grammar.",

keywords = "Global reordering, Machine translation, Non-isomorphic tree-to-tree mapping, Synchronous tree-substitution-grammar, Tree-to-tree model",

author = "Jiang, \{Hong Fei\} and Sheng Li and Fu, \{Guo Hong\} and Zhao, \{Tie Jun\} and Min Zhang",

year = "2009",

month = may,

doi = "10.3724/SP.J.1001.2009.03409",

language = "英语",

volume = "20",

pages = "1241--1253",

journal = "Ruan Jian Xue Bao/Journal of Software",

issn = "1000-9825",

publisher = "Chinese Academy of Sciences",

number = "5",

}

TY - JOUR

T1 - Statistical machine translation model based on a synchronous tree-substitution grammar

AU - Jiang, Hong Fei

AU - Li, Sheng

AU - Fu, Guo Hong

AU - Zhao, Tie Jun

AU - Zhang, Min

PY - 2009/5

Y1 - 2009/5

N2 - A translation model based on synchronous tree-substitution-grammar is presented in this paper. It can elegantly model the global reordering and discontinuous phrases. Furthermore, it can learn non-isomorphic tree-to-tree mappings. Experimental results on two different data sets show that the proposed model significantly outperforms the phrase-based model and the model based on synchronous context-free grammar.

AB - A translation model based on synchronous tree-substitution-grammar is presented in this paper. It can elegantly model the global reordering and discontinuous phrases. Furthermore, it can learn non-isomorphic tree-to-tree mappings. Experimental results on two different data sets show that the proposed model significantly outperforms the phrase-based model and the model based on synchronous context-free grammar.

KW - Global reordering

KW - Machine translation

KW - Non-isomorphic tree-to-tree mapping

KW - Synchronous tree-substitution-grammar

KW - Tree-to-tree model

UR - https://www.scopus.com/pages/publications/65749110133

U2 - 10.3724/SP.J.1001.2009.03409

DO - 10.3724/SP.J.1001.2009.03409

M3 - 文章

AN - SCOPUS:65749110133

SN - 1000-9825

VL - 20

SP - 1241

EP - 1253

JO - Ruan Jian Xue Bao/Journal of Software

JF - Ruan Jian Xue Bao/Journal of Software

IS - 5

ER -

Statistical machine translation model based on a synchronous tree-substitution grammar

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this