摘要
本文给出了BT863Ⅱ英汉机器翻译中,规则和统计方法并举的译文选择策略。基于规则的译文选择方法主要通过考察英语单词在一定上下文中的句法和语义特征,形成支持译文选择的规则;基于统计的译文选择方法是在目标语二元统计的基础上,针对待翻译的英语句子形成消歧矩阵,对消歧矩阵采用了一种贪心搜索策略进行译文选择。
The methods of translation selection used in BT863 Ⅱ English Chinese machine translation is introduced,which is hybrid strategy combining rule based and statistic based methods.As to rule based method,it is implemented through observing and studying the characteristics of the contexts of ambiguating English word and giving the rules of disambiguation;as to the statistic based method,it is based on the Bigram used in target language,further a disambiguation matrix is built and a greed search strategy is used to translation selection.
出处
《情报学报》
CSSCI
北大核心
1999年第2期99-104,共6页
Journal of the China Society for Scientific and Technical Information
基金
国家863计划
国家自然科学基金