论文部分内容阅读
提出一种利用翻译词对信息快速构建知识组织系统中术语之间同义关系的方法:利用单词条的翻译数量、翻译共现强度等作为基本输入,通过简单布尔判断、条件互信息或向量空间模型余弦相似度来计算术语之间的相似度,进而发现并构建同义关系;采用准确率和丰富率来评价构建效果,通过在新能源汽车领域进行实验,发现该方法不但速度快,而且在翻译信息比较丰富的条件下,对于中文同义关系构建有较好效果。
This paper proposes a method to construct the synonymous relationship between terms in knowledge organization system by using translation words: using the number of translations, the strength of translation co-occurrence as the basic input, through simple Boolean decision, conditional mutual information or vector Space model cosine similarity to calculate the similarity between the terms, and then find and construct the synonymous relationship; using the accuracy and richness to evaluate the construction effect, through experiments in the field of new energy vehicles found that the method is not only fast, and Under the condition of rich information of translation, it has a good effect on constructing the Chinese synonymous relationship.