Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
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. . | A Statistical Machine Translation Model Based on a Synthetic Synchronous Grammar Hongfei Jiang Muyun Yang Tiejun Zhao Sheng Li and Bo Wang School of Computer Science and Technology Harbin Institute of Technology hfjiang ymy tjzhao lisheng bowang @mtlab.hit.edu.cn 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. 1 Introduction The use of various synchronous grammar based formalisms has been a trend for statistical machine translation SMT Wu 1997 Eisner 2003 Galley et al. 2006 Chiang 2007 Zhang et al. 2008 . The grammar formalism determines the intrinsic capacities and computational efficiency of the SMT systems. To evaluate the capacity of a grammar formalism two factors i.e. generative power and expressive power are usually considered Su and Chang 1990 . The generative power refers to the ability to generate the strings of the language and the expressive power to the ability to describe the same language with fewer or no extra ambiguities. For the current synchronous grammars based SMT to some extent the generalization ability of the grammar rules the usability of the rules for the new sentences can be considered as a kind of the generative power of the grammar and the disam- biguition ability to the rule candidates can be considered as an embodiment of expressive power. However the generalization ability and the dis-ambiguition .
