240_面向篇章机器翻译的英汉翻译单位和翻译模型研究.pdfVIP

* 面向篇章机器翻译的英汉翻译单位和翻译模型研究 宋柔，葛诗利 广东外语外贸大学外语研究与语言服务协同创新中心，广东广州510420 摘要：篇章机器翻译的首要问题是确定翻译单位。基于汉语和英语的语言知识和英汉翻译的实践，本文提 出面向篇章机器翻译的基本单位和复合单位的双层单位体系，讨论了这两种单位支持篇章翻译应满足的性 质，并据此勾画了篇章机器翻译的拆分、翻译、装配三步模型 （PTA 模型）。本文提出，汉语篇章机器翻译 的复合单位为广义话题结构对应的文本块，基本单位则是根据广义话题结构流水模型得到的话题自足句； 英语篇章机器翻译的复合单位为句号句，基本单位为naming-telling 小句（NT 小句），即指称性成分加上对 它的陈述或后修饰成分所构成的小句。本文展示了在这样的翻译单位体系下采用 PTA 模型的英汉翻译过程 实例，规划了面向篇章翻译的英汉小句对齐语料库的建设任务，讨论了PTA 模型的可行性。 关键词：翻译单位；翻译模型；广义话题结构；naming-telling 小句 English-Chinese Translation Unit and Translation Model for Discourse-Based Machine Translation Rou Song, Shili Ge Guangdong Collaborative Innovation Center for Language Research Services, Guangdong University of Foreign Studies, Guangzhou, Guangdong 510420, China Abstract: The primary issue in discourse-based machine translation (MT) is to define translation unit. Based on English and Chinese linguistic knowledge and English-Chinese translation practice, we propose a double level system of translation unit, including basic unit and compound unit, for discourse-based MT. We further explore the required properties of these two types of units and construct a three-step model of parsing, translating and assembling (PTA model) in support of discourse-based MT. This paper indicates that the compound unit for Chinese discourse-based MT is the text in correspondence to generalized topic structure and the basic unit is the topic sufficient sentence derived from the stream model of generalized topic structure, while the compound unit for English is the traditional sentence and the basic unit is the naming-telling clause (NT clause), namely, the clause constructed with the referential component and its description or post-modification component. This