| 摘要: |
| 提出一种基于同步树替换文法的机器翻译模型.相对于基于短语的模型,此模型可以对远距离结构性调序和非连续短语翻译进行建模;相对于基于同步上下文无关文法模型,此模型可以对任何层次上的树节点调序进行建模.因此,该模型可以为处理语言结构间的异构对应问题提供有效的解决途径. 在两组风格差异较大的数据集上进行的实验均验证了基于同步树替换文法的模型相对于基于短语模型和基于同步上下文无关文法模型的稳定优势. |
| 关键词: 机器翻译 同步树替换文法 树到树模型 全局调序 异构对应 |
| DOI： |
| 分类号: |
| 基金项目:Supported by the National Natural Science Foundation of China under Grant No.60736014 (国家自然科学基金); the National High-Tech Research and Development Plan of China under Grant No.2006AA010108 (国家高技术研究发展计划(863)) |
|
| Statistical Machine Translation Model Based on a Synchronous Tree-Substitution Grammar |
|
JIANG Hong-Fei,LI Sheng,FU Guo-Hong,ZHAO Tie-Jun,ZHANG Min
|
| 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. |
| Key words: machine translation synchronous tree-substitution-grammar tree-to-tree model global reordering non-isomorphic tree-to-tree mapping |
