论文部分内容阅读
文章归纳整理了藏文网页的结构特征,在借鉴中英文关键词抽取方法的基础上,设计实现了融合语义知识的藏文网页关键词抽取算法。该算法利用藏文文本特征实现了网页内容模块的智能识别,在对识别的文本块进行自动分词后,采用改进的TF-IDF算法得到基础词集,然后根据词向量特征进行基础词的语义扩展构建候选关键词集,最后利用候选关键词之间的语义相关度值,确立藏文网页的关键词。藏文网页的实验测试结果表明该方法提取的藏文网页关键词具有较高的准确率。
This paper summarizes the structural features of Tibetan web pages. Based on the reference of Chinese and English keyword extraction methods, this paper designs and implements the key words extraction algorithm of Tibetan web pages that integrates semantic knowledge. The algorithm uses the Tibetan text feature to realize the intelligent recognition of the webpage content module. After the automatic segmentation of the identified text block, the improved TF-IDF algorithm is used to get the basic wordset, and then the semantic expansion of the basic word Build a set of candidate keywords, and finally make use of the semantic relevancy between the candidate keywords to establish the key words of Tibetan web pages. The experimental results of Tibetan web pages show that the keywords of Tibetan web pages extracted by this method have high accuracy.