A Statistical Machine Translation Model Based on a Synthetic Synchronous Grammar

Hongfei Jiang; Muyun Yang; Tiejun Zhao; Sheng Li; Bo Wang

A Statistical Machine Translation Model Based on a Synthetic Synchronous Grammar

Hongfei Jiang
, Muyun Yang
, Tiejun Zhao
, Sheng Li
, Bo Wang

School of Computer Science and Technology, Harbin Institute of Technology

Research output: Contribution to conference › Paper › peer-review

3 Scopus citations

Abstract

Recently, various synchronous grammars are proposed for syntax-based machine translation, e.g. synchronous context-free grammar and synchronous tree (sequence) substitution grammar, either purely formal or linguistically motivated. Aiming at combining the strengths of different grammars, we describes a synthetic synchronous grammar (SSG), which tentatively in this paper, integrates a synchronous context-free grammar (SCFG) and a synchronous tree sequence substitution grammar (STSSG) for statistical machine translation. The experimental results on NIST MT05 Chinese-to-English test set show that the SSG based translation system achieves significant improvement over three baseline systems.

Original language	English
Pages	125-128
Number of pages	4
State	Published - 2009
Externally published	Yes
Event	Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009 - Suntec, Singapore Duration: 2 Aug 2009 → 7 Aug 2009

Conference

Conference	Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009
Country/Territory	Singapore
City	Suntec
Period	2/08/09 → 7/08/09

Cite this

Jiang, H., Yang, M., Zhao, T., Li, S., & Wang, B. (2009). A Statistical Machine Translation Model Based on a Synthetic Synchronous Grammar. 125-128. Paper presented at Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009, Suntec, Singapore.

Jiang, Hongfei ; Yang, Muyun ; Zhao, Tiejun et al. / A Statistical Machine Translation Model Based on a Synthetic Synchronous Grammar. Paper presented at Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009, Suntec, Singapore.4 p.

@conference{d36c0e11463b4cbeb634bd9dde3b753f,

title = "A Statistical Machine Translation Model Based on a Synthetic Synchronous Grammar",

abstract = "Recently, various synchronous grammars are proposed for syntax-based machine translation, e.g. synchronous context-free grammar and synchronous tree (sequence) substitution grammar, either purely formal or linguistically motivated. Aiming at combining the strengths of different grammars, we describes a synthetic synchronous grammar (SSG), which tentatively in this paper, integrates a synchronous context-free grammar (SCFG) and a synchronous tree sequence substitution grammar (STSSG) for statistical machine translation. The experimental results on NIST MT05 Chinese-to-English test set show that the SSG based translation system achieves significant improvement over three baseline systems.",

author = "Hongfei Jiang and Muyun Yang and Tiejun Zhao and Sheng Li and Bo Wang",

note = "Publisher Copyright: {\textcopyright} 2009 ACL and AFNLP; Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009 ; Conference date: 02-08-2009 Through 07-08-2009",

year = "2009",

language = "英语",

pages = "125--128",

}

Jiang, H, Yang, M , Zhao, T, Li, S & Wang, B 2009, 'A Statistical Machine Translation Model Based on a Synthetic Synchronous Grammar', Paper presented at Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009, Suntec, Singapore, 2/08/09 - 7/08/09 pp. 125-128.

A Statistical Machine Translation Model Based on a Synthetic Synchronous Grammar. / Jiang, Hongfei; Yang, Muyun ; Zhao, Tiejun et al.
2009. 125-128 Paper presented at Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009, Suntec, Singapore.

Research output: Contribution to conference › Paper › peer-review

TY - CONF

T1 - A Statistical Machine Translation Model Based on a Synthetic Synchronous Grammar

AU - Jiang, Hongfei

AU - Yang, Muyun

AU - Zhao, Tiejun

AU - Li, Sheng

AU - Wang, Bo

PY - 2009

Y1 - 2009

N2 - Recently, various synchronous grammars are proposed for syntax-based machine translation, e.g. synchronous context-free grammar and synchronous tree (sequence) substitution grammar, either purely formal or linguistically motivated. Aiming at combining the strengths of different grammars, we describes a synthetic synchronous grammar (SSG), which tentatively in this paper, integrates a synchronous context-free grammar (SCFG) and a synchronous tree sequence substitution grammar (STSSG) for statistical machine translation. The experimental results on NIST MT05 Chinese-to-English test set show that the SSG based translation system achieves significant improvement over three baseline systems.

AB - Recently, various synchronous grammars are proposed for syntax-based machine translation, e.g. synchronous context-free grammar and synchronous tree (sequence) substitution grammar, either purely formal or linguistically motivated. Aiming at combining the strengths of different grammars, we describes a synthetic synchronous grammar (SSG), which tentatively in this paper, integrates a synchronous context-free grammar (SCFG) and a synchronous tree sequence substitution grammar (STSSG) for statistical machine translation. The experimental results on NIST MT05 Chinese-to-English test set show that the SSG based translation system achieves significant improvement over three baseline systems.

UR - https://www.scopus.com/pages/publications/84859905732

M3 - 论文

AN - SCOPUS:84859905732

SP - 125

EP - 128

T2 - Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009

Y2 - 2 August 2009 through 7 August 2009

ER -

A Statistical Machine Translation Model Based on a Synthetic Synchronous Grammar

Abstract

Conference

Other files and links

Fingerprint

Cite this