【摘要】 句子间相似度的计算在自然语言处理的各个领域都占有很重要的地位,在多文档自动文摘技术中,句子间相似度的计算是一个关键的问题。由于汉语句子的表达形式是多种多样的,要准确地刻画一个句子所表达的意思,必须深入到语义一级并结合语法结构信息,由此提出了一种基于语义依存的汉语句子相似度计算的方法,该方法取得了令人满意的实验效果。更多还原

【Abstract】 Sentence similarity computation is very important in all the fields of Natural Language Processing.In Multi-document Summarization Technology,sentence similarity computation is a key problem.As we know,a Chinese sentence can be presented by many kinds of style,if we want to describe what a sentence means,we should dip into the semantic level and consider about the dependency structure.In this paper,we applied a method that based on semantic dependency relationship analysis to compute sentence similarity,and the experiment result of this method is satisfied.更多还原