【作者】 姚建民； 张晶； 赵铁军； 于浩； 李生；

【Author】 Yao Jianmin, Zhang Jing, Zhao Tiejun, Yu Hao, Li ShengSchool of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001

【机构】 哈尔滨工业大学计算机科学与技术学院；

【摘要】 介绍了MTS2000英汉机器翻译系统中译文选择和转换生成的实现策略.基于句法结构的译文选择将句法上下文集合视为词包,统计集合中各词的词信息和词性信息作为上下文特征,以Bayes最小错误概率公式作为评价函数选择译文.基于规则的转换生成模块在句法分析树的基础上,利用词性、语义,甚至词特征进行源语言句法树向目标语句法树的转换.更多还原

【Abstract】 The translation choice and transfer modules in the English Chinese machine translation system of MTS2000 are introduced. The translation choice is realized on the basis of a grammar tree and takes the context as a word bag, with the lexicon and POS tag information as context features. The Bayes minimal error probability is taken as the evaluation function of the candidate translation. The rule-based transfer and generation module takes the parsing tree as input and operates on the information of POS tag, semantics or even the lexicon.更多还原