| 摘要: |
| 提出了一种基于E-Chunk的多引擎机器翻译模型.该模型以中心语驱动的分析技术为基础,通过词汇相似特征计算E-Chunk的匹配代价,自底向上地完成最优E-Chunk覆盖的构造,并以E-Chunk为基本翻译单元完成机器翻译过程.初步的实验结果显示,该方法在面向领域文本的自动翻译方面是有效的. |
| 关键词: E-Chunk 机器翻译 词汇相似计算 |
| DOI： |
| 分类号: |
| 基金项目:国家自然科学基金资助项目(69985001);国家重点基础研究973资助项目(G19980305011);国家教育部博士点基金资助项目(1999014503) |
|
| A Machine Translation Model Based on E-Chunk |
|
LI Mu,LU Xue-qiang,YAO Tian-shun
|
| Abstract: |
| In this paper, a new E-Chunk based multi-engine machine translation model is proposed. The model is composed of a head-driven lexicalized parser, a word-similarity based E-Chunk match engine and a bilingual E-Chunk based transfer engine. The optimal E-Chunk tiling is constructed in a bottom-up style efficiently. Preliminary experimental results show that it is effective in domain oriented machine translation. |
| Key words: E-Chunk machine translation word similarity computation |
